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

    Neuronpedia

    INDEX
    Explanations

    COSO Framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    he
    2.15
    いる
    1.93
    \{
    1.73
    ек
    1.59
    ic
    1.57
    𝑒
    1.56
    ंती
    1.55
    Ys
    1.54
     casual
    1.53
    itriangular
    1.50
    POSITIVE LOGITS
     manifestly
    1.84
    гідно
    1.78
     siendo
    1.76
    ようになった
    1.73
    वियस
    1.73
    至於
    1.73
    seits
    1.69
    ﻕ
    1.67
    ⃞
    1.66
    ות
    1.65
    Act Density 0.000%

    No Known Activations