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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lighter
    -0.06
     батьків
    -0.06
    _IDENTIFIER
    -0.06
     ilg
    -0.06
     ребенок
    -0.06
    .Reg
    -0.06
    ئ
    -0.06
    SectionsIn
    -0.06
     epid
    -0.06
     सद
    -0.06
    POSITIVE LOGITS
    撤
    0.07
     TBD
    0.07
    (logging
    0.07
     Jake
    0.07
    made
    0.06
    duration
    0.06
     jLabel
    0.06
     Mur
    0.06
    점
    0.06
     roce
    0.06
    Act Density 0.016%

    No Known Activations