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

    Neuronpedia

    INDEX
    Explanations

    full stops followed by extra whitespace, or a few negative sentiment words

    oai_token-act-pair · gemini-2.0-flash

    factual report excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    væ
    -0.52
    ழு
    -0.48
     convient
    -0.48
    Salmo
    -0.48
    OneToMany
    -0.47
    に触
    -0.47
     сна
    -0.46
    TT
    -0.46
    Affirmed
    -0.46
    тал
    -0.44
    POSITIVE LOGITS
    ArrowToggle
    0.74
     InputDecoration
    0.70
    ंदीखरीदारी
    0.70
    parsedMessage
    0.69
    rrggbb
    0.64
    ttemberg
    0.62
     Theſe
    0.60
    帖最后由
    0.60
    jooq
    0.57
     AssemblyTitle
    0.57
    Act Density 2.205%

    No Known Activations