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

    Neuronpedia

    INDEX
    Explanations

    Dense, Dropout, Activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.71
    ot
    0.71
     A
    0.70
     (
    0.69
    ana
    0.68
    ES
    0.68
     a
    0.66
    ai
    0.66
    </h2>
    0.62
    O
    0.61
    POSITIVE LOGITS
     interrump
    0.66
    𝚋
    0.65
     prefque
    0.64
     mỹ
    0.63
     remplacement
    0.63
     bunyi
    0.62
     arabe
    0.61
    𝒕
    0.61
    有點
    0.61
     ainfi
    0.61
    Act Density 0.001%

    No Known Activations