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

    Neuronpedia

    INDEX
    Explanations

    Jennies party

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হাজির
    1.78
     публику
    1.67
     désir
    1.66
    ساوي
    1.66
     पासून
    1.65
    ennen
    1.65
    ائج
    1.64
    Prix
    1.63
    𝓭
    1.61
    ERGY
    1.60
    POSITIVE LOGITS
     quod
    1.71
    ur
    1.68
    hash
    1.65
    inplace
    1.61
    is
    1.53
    ि
    1.53
     наме
    1.45
     JHEP
    1.44
    nodo
    1.43
    on
    1.42
    Act Density 0.000%

    No Known Activations