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

    Neuronpedia

    INDEX
    Explanations

    Innovation catalyst and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    1.05
    v
    0.83
    니
    0.77
    বার
    0.76
     This
    0.75
    จะ
    0.74
    開始
    0.73
     predicament
    0.72
     kini
    0.72
     یہ
    0.70
    POSITIVE LOGITS
    ه
    1.35
    0
    1.27
    a
    1.20
    <0x80>
    1.13
    σεις
    1.06
    ０
    1.06
    া
    1.02
    rir
    0.94
    risch
    0.94
    innov
    0.94
    Act Density 0.009%

    No Known Activations