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

    Neuronpedia

    INDEX
    Explanations

    DoF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ts
    0.45
    InitTypeDef
    0.43
    theme
    0.42
    iglie
    0.40
    vec
    0.40
    ^{[\
    0.40
    connectivity
    0.40
     oedd
    0.39
    '][
    0.39
     vint
    0.39
    POSITIVE LOGITS
     opération
    0.44
    观看
    0.42
    ільки
    0.41
    ర్మ
    0.41
     conscious
    0.41
    거나
    0.41
    仅
    0.41
     yalnızca
    0.40
    ્યારે
    0.40
     Fernseh
    0.40
    Act Density 0.005%

    No Known Activations