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

    Neuronpedia

    INDEX
    Explanations

    $fillable properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дит
    1.92
    ding
    1.76
     zara
    1.73
    shareButton
    1.73
    殑
    1.68
    з
    1.67
    chomp
    1.66
    ଼
    1.64
     зна
    1.62
    ंखला
    1.60
    POSITIVE LOGITS
    多い
    2.06
    ㅉ
    2.04
     desse
    2.00
     objectifs
    1.96
    ことも
    1.90
    েরা
    1.87
     setzen
    1.86
     selatan
    1.83
     områ
    1.82
     neutrals
    1.81
    Act Density 0.000%

    No Known Activations