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

    Neuronpedia

    INDEX
    Explanations

    ass, donkey, camel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.78
    t
    0.70
    n
    0.66
    вання
    0.63
    a
    0.63
    o
    0.62
    *
    0.62
    r
    0.61
    נ
    0.60
    σεις
    0.59
    POSITIVE LOGITS
     마
    0.59
     as
    0.57
     På
    0.56
    ale
    0.55
     sedimentary
    0.55
     lounging
    0.54
     twee
    0.53
     Vous
    0.52
     אחת
    0.52
    การ
    0.52
    Act Density 0.002%

    No Known Activations