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

    Neuronpedia

    INDEX
    Explanations

    lines

    np_max-act · gemini-2.0-flash

    This neuron detects block‐comment banner lines—long runs of punctuation (e.g. “/*…*******/”) used as section or header separators.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    　　　　　
    -0.07
    　　
    -0.07
     爱
    -0.06
    ($"{
    -0.06
    (ag
    -0.06
    وغ
    -0.06
    γ
    -0.06
    인증
    -0.06
    　　　
    -0.06
    　　　　　　　　
    -0.06
    POSITIVE LOGITS
     Stellar
    0.08
    raph
    0.07
     erhalten
    0.07
    ENSE
    0.06
     �
    0.06
    _vs
    0.06
     Relax
    0.06
    術
    0.06
    _picture
    0.06
     Grinder
    0.06
    Act Density 0.003%

    No Known Activations