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

    Neuronpedia

    INDEX
    Explanations

    probability and repeated attempts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    筒
    -0.06
    訊
    -0.06
     отд
    -0.06
    姆
    -0.05
    <<
    -0.05
    958
    -0.05
    -risk
    -0.05
     evet
    -0.05
    68
    -0.05
     userdata
    -0.05
    POSITIVE LOGITS
     rodiny
    0.07
    няет
    0.07
    cljs
    0.07
    avez
    0.07
     ballpark
    0.07
    <Path
    0.06
     ウ
    0.06
    рощ
    0.06
    าคม
    0.06
    ordering
    0.06
    Act Density 0.014%

    No Known Activations