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

    Neuronpedia

    INDEX
    Explanations

    dominant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.67
    ionario
    -0.63
    verwijspagina
    -0.61
     للاسماء
    -0.60
    quelles
    -0.60
     giustizia
    -0.60
     himo
    -0.59
     vastaan
    -0.59
     חיצוניים
    -0.58
     miljoner
    -0.58
    POSITIVE LOGITS
     mechanism
    0.61
    akos
    0.55
    ollectionView
    0.53
    lan
    0.53
    ak
    0.52
     Mechanism
    0.52
    kec
    0.52
    Eloquent
    0.51
     trasfer
    0.51
    ampi
    0.51
    Act Density 0.590%

    No Known Activations