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

    Neuronpedia

    INDEX
    Explanations

    words starting with "al" or "occ"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsr
    0.79
    شور
    0.77
     potassium
    0.74
    নু
    0.71
    輳
    0.69
     js
    0.69
     boron
    0.68
    fuss
    0.66
    ত্তির
    0.65
     స్ప
    0.65
    POSITIVE LOGITS
    Alban
    0.90
    alien
    0.89
     alakalı
    0.86
    Ala
    0.85
    Ald
    0.84
    Ale
    0.84
    됩니다
    0.83
    alé
    0.83
    alde
    0.82
    alena
    0.81
    Act Density 0.039%

    No Known Activations