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

    Neuronpedia

    INDEX
    Explanations

    parentheses/brackets

    np_max-act · gemini-2.0-flash

    The neuron fires on boilerplate legal/license headers (e.g. Copyright and Apache-style license notices).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (pad
    -0.07
     जबक
    -0.07
    acciones
    -0.06
    _OS
    -0.06
    ैठ
    -0.06
    Opened
    -0.06
    SELF
    -0.06
    ===========↵
    -0.06
    nostic
    -0.06
    الك
    -0.06
    POSITIVE LOGITS
    .“
    0.07
     uy
    0.06
     температу
    0.06
     마음
    0.06
    186
    0.06
     marshal
    0.06
    utf
    0.06
    vault
    0.06
     amour
    0.06
    ฬ
    0.06
    Act Density 0.005%

    No Known Activations