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

    Neuronpedia

    INDEX
    Explanations

    vice versa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bas
    0.72
    Bas
    0.66
    ToBase
    0.66
     Bas
    0.65
     basal
    0.63
    δί
    0.62
    Prol
    0.62
     etiqueta
    0.61
     Gaff
    0.61
     patty
    0.61
    POSITIVE LOGITS
    coran
    0.76
    versed
    0.66
    versi
    0.65
     Vers
    0.62
    铐
    0.61
    versa
    0.59
    Vers
    0.58
    ಔ
    0.58
    ruciating
    0.58
    不成
    0.57
    Act Density 0.174%

    No Known Activations