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

    Neuronpedia

    INDEX
    Explanations

    d&d editions and dice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    來說
    0.88
     anál
    0.84
     cres
    0.83
     taman
    0.82
     Disha
    0.82
     phonons
    0.82
    禮
    0.82
    ২২
    0.81
    hoch
    0.81
    ડિયો
    0.80
    POSITIVE LOGITS
    ao
    0.98
    c
    0.95
    is
    0.94
    ください
    0.86
    ll
    0.82
    z
    0.82
    ae
    0.81
    al
    0.80
    es
    0.80
    as
    0.77
    Act Density 0.001%

    No Known Activations