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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _script
    -0.06
    ضر
    -0.06
     crumbs
    -0.06
     hashtag
    -0.06
    xfa
    -0.06
     cartridge
    -0.06
     σου
    -0.06
     ");
    -0.06
    часно
    -0.06
    choose
    -0.06
    POSITIVE LOGITS
     Sequence
    0.07
    -generation
    0.07
    统计
    0.07
     scans
    0.07
     Plex
    0.06
     fighters
    0.06
     Elijah
    0.06
     aller
    0.06
     Fairy
    0.06
    _pdf
    0.06
    Act Density 0.026%

    No Known Activations