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

    Neuronpedia

    INDEX
    Explanations

    Machinery descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =>
↵
    -0.08
    anford
    -0.07
     extraordinarily
    -0.07
    (mx
    -0.07
    消费需求
    -0.06
    политическ
    -0.06
    .MILLISECONDS
    -0.06
    естественн
    -0.06
    �습니다
    -0.06
    ||(
    -0.06
    POSITIVE LOGITS
     kings
    0.07
    lene
    0.07
    ость
    0.07
     Slider
    0.07
    _MARKER
    0.07
     instal
    0.07
    From
    0.06
     suppressing
    0.06
    팅
    0.06
    BA
    0.06
    Act Density 0.044%

    No Known Activations