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

    Neuronpedia

    INDEX
    Explanations

    time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вам
    -0.07
    _email
    -0.06
     Cran
    -0.06
     Frame
    -0.06
     víc
    -0.06
    生成
    -0.06
    ojis
    -0.06
    반기
    -0.06
    브
    -0.06
     shop
    -0.06
    POSITIVE LOGITS
    [Unit
    0.07
     Senators
    0.07
     Capitals
    0.06
     IND
    0.06
    (BASE
    0.06
     Strict
    0.06
    .checkSelfPermission
    0.06
     скры
    0.06
     رسم
    0.06
    #,
    0.06
    Act Density 0.020%

    No Known Activations