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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wayback
    -0.66
     Roskov
    -0.61
    ikin
    -0.57
    WEBPACK
    -0.55
    tableFuture
    -0.54
     Walkover
    -0.54
     дово
    -0.54
    awtextra
    -0.53
    tocin
    -0.52
     coils
    -0.52
    POSITIVE LOGITS
     døde
    0.61
     Drapeau
    0.61
     vicenda
    0.58
     '\\;'
    0.53
    хьтан
    0.50
     ansatte
    0.50
     støtte
    0.49
    seitig
    0.49
    €¦
    0.49
     autorytatywna
    0.48
    Act Density 0.230%

    No Known Activations