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

    Neuronpedia

    INDEX
    Explanations

    programming languages and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offenders
    0.62
     liabilities
    0.62
     odors
    0.61
     abortions
    0.57
     মায়ের
    0.55
     smears
    0.54
     pollutants
    0.54
     violators
    0.54
     dyes
    0.53
     blisters
    0.53
    POSITIVE LOGITS
    k
    0.91
    a
    0.88
    in
    0.71
    ne
    0.70
    g
    0.69
    ly
    0.66
    d
    0.65
    re
    0.64
    te
    0.64
    st
    0.64
    Act Density 0.054%

    No Known Activations