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

    Neuronpedia

    INDEX
    Explanations

    avoiding specific acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأساس
    0.42
    ratingBarStyle
    0.39
     let
    0.38
    Cert
    0.38
    უხ
    0.37
     display
    0.37
     男性用
    0.37
     cré
    0.37
    ΟΣ
    0.37
     rozp
    0.37
    POSITIVE LOGITS
     очеред
    0.50
    俨
    0.48
    copic
    0.46
     triads
    0.45
    -
    0.45
    nge
    0.45
     какая
    0.45
    lir
    0.45
    brenner
    0.45
    lope
    0.44
    Act Density 0.002%

    No Known Activations