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

    Neuronpedia

    INDEX
    Explanations

    normally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     normally
    -1.41
    normally
    -1.16
     Normally
    -1.05
     ordinarily
    -1.00
     normal
    -0.96
    Normally
    -0.93
     normalement
    -0.92
     normale
    -0.91
     normalmente
    -0.91
    normal
    -0.84
    POSITIVE LOGITS
     nakalista
    0.75
     kasarigan
    0.69
     صوتيه
    0.63
     EconPapers
    0.59
     Tapatalk
    0.59
    ########.
    0.56
    contentLoaded
    0.54
    KommentareTeilen
    0.54
    ConstraintMaker
    0.52
     EClass
    0.52
    Act Density 0.056%

    No Known Activations