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

    Neuronpedia

    INDEX
    Explanations

    variable expansion using curly braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    免許
    0.44
    woorden
    0.42
    Swan
    0.41
    édé
    0.40
    auft
    0.39
    FBSDKLogin
    0.39
    CreateCharacter
    0.39
    klärung
    0.38
     dystrophy
    0.38
     건
    0.37
    POSITIVE LOGITS
     expressions
    0.95
     Expressions
    0.91
     expression
    0.89
     interpolated
    0.88
     interpolation
    0.86
     interpol
    0.86
     Expression
    0.85
     expressões
    0.84
    expression
    0.84
     interpolate
    0.82
    Act Density 0.034%

    No Known Activations