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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	fire
    -0.07
    _attachments
    -0.06
     collector
    -0.06
    AVOR
    -0.06
    .sel
    -0.06
    	internal
    -0.06
     萬
    -0.06
    -0.06
    .win
    -0.06
     Ambassador
    -0.06
    POSITIVE LOGITS
    _strlen
    0.07
     passport
    0.06
     Automatically
    0.06
    iner
    0.06
    val
    0.06
    -date
    0.06
    won
    0.06
    (credentials
    0.06
    بات
    0.06
    Ｓ
    0.06
    Act Density 0.000%

    No Known Activations