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

    Neuronpedia

    INDEX
    Explanations

    in excessive doses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     filing
    1.11
     prof
    1.01
     Unemployment
    0.99
     const
    0.99
    是的
    0.95
    ll
    0.94
    adios
    0.94
     salaries
    0.92
     unemployment
    0.92
     hesitate
    0.92
    POSITIVE LOGITS
    া
    1.54
    ליך
    1.46
    diendo
    1.41
    ați
    1.38
    tı
    1.35
     cellulaire
    1.35
     веществ
    1.31
    ה
    1.30
    ции
    1.28
    aime
    1.28
    Act Density 0.000%

    No Known Activations