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

    Neuronpedia

    INDEX
    Explanations

    resource links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olith
    1.15
    angle
    1.10
    olib
    1.09
    open
    1.08
    センチ
    1.08
    mud
    1.07
    quin
    1.06
    uset
    1.05
    angin
    1.04
    pint
    1.04
    POSITIVE LOGITS
     rám
    0.97
     aided
    0.96
     الأمر
    0.94
     Vorstand
    0.94
     당
    0.93
     arriba
    0.91
     اتفاق
    0.91
     miembros
    0.91
    Decedent
    0.91
    hereinafter
    0.90
    Act Density 0.095%

    No Known Activations