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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or chemical notation

    np_acts-logits-general · gemini-2.0-flash

    symbols, LaTeX, and CD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мәкал
    -0.55
    tagHelperRunner
    -0.51
    archiviato
    -0.44
    SourceChecksum
    -0.44
     Turquie
    -0.44
     Grèce
    -0.43
     Colombie
    -0.41
     Normdatei
    -0.40
    UnusedPrivate
    -0.40
     pinulongan
    -0.38
    POSITIVE LOGITS
    🟤
    0.56
     royal
    0.50
     main
    0.48
     Bancroft
    0.48
     Royal
    0.47
    MessageOf
    0.47
    delwed
    0.46
    NOPQRST
    0.46
     shit
    0.46
    shit
    0.45
    Act Density 2.406%

    No Known Activations