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

    Neuronpedia

    INDEX
    Explanations

    future

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $update
    -0.07
     '//
    -0.06
    找到
    -0.06
     svého
    -0.06
     Austral
    -0.06
    덤프
    -0.06
     Cathy
    -0.06
    іє
    -0.06
    イズ
    -0.06
     Hart
    -0.06
    POSITIVE LOGITS
     hoy
    0.07
     �
    0.06
    _interrupt
    0.06
    785
    0.06
     Sp
    0.06
    (separator
    0.06
    ่าท
    0.06
     Prec
    0.06
    .bounds
    0.06
    scal
    0.06
    Act Density 0.010%

    No Known Activations