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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    Python code snippets and examples related to random number generation.

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

    This neuron remains inactive on all input tokens and thus does not detect any specific feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _k
    -0.06
    iale
    -0.06
    #pragma
    -0.06
    #ifndef
    -0.06
     youre
    -0.06
    NOT
    -0.06
    .ke
    -0.06
    767
    -0.06
    하려
    -0.06
    …but
    -0.06
    POSITIVE LOGITS
    =""
    0.07
    (ord
    0.07
    )”
    0.07
    ़
    0.07
     Федера
    0.07
     أد
    0.07
     quyền
    0.06
     mệnh
    0.06
    //"
    0.06
    ")}
    0.06
    Act Density 0.314%

    No Known Activations