Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash

    code snippets and technical documentation related to programming practices and structures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to CamelCase (or all‐caps) code identifiers—i.e. class/type names in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    PLICATION
    -0.06
    _latency
    -0.06
    **↵
    -0.06
    ////////////////////////////////////////////////////////
    -0.06
    ��
    -0.06
     Django
    -0.06
    ISTRY
    -0.06
    ottes
    -0.06
     shuts
    -0.06
    ▲
    -0.06
    POSITIVE LOGITS
     '#'
    0.07
    >s
    0.07
     뛰
    0.06
     refl
    0.06
     emerg
    0.06
     Vacc
    0.06
    USH
    0.06
     vibration
    0.06
    ida
    0.06
    umb
    0.06
    Act Density 0.049%

    No Known Activations