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

    Neuronpedia

    INDEX
    Explanations

    uses of the word "nice."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wors
    -0.69
    tagHelperRunner
    -0.69
    cular
    -0.67
     Kl
    -0.66
     mutagen
    -0.65
    FailureListener
    -0.65
    ThemeOverlay
    -0.65
    ✱
    -0.63
     racket
    -0.62
    pubsub
    -0.61
    POSITIVE LOGITS
     NICE
    0.88
     nice
    0.77
    NICE
    0.74
    nice
    0.70
    ymce
    0.69
    prettier
    0.69
    😏
    0.67
     Nice
    0.66
    porsche
    0.66
     Sich
    0.65
    Act Density 0.005%

    No Known Activations