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

    Neuronpedia

    INDEX
    Explanations

    search engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    様々な
    0.77
    積極的に
    0.76
     olyan
    0.75
    étape
    0.75
    Botan
    0.74
    jekte
    0.73
    Legisl
    0.73
    INCREMENT
    0.72
     أ
    0.72
     einzelnen
    0.71
    POSITIVE LOGITS
     and
    0.78
     If
    0.77
     prevention
    0.77
     quies
    0.77
     nếu
    0.76
     discrimination
    0.75
     if
    0.75
     soundness
    0.74
     faults
    0.73
     predation
    0.73
    Act Density 0.000%

    No Known Activations