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

    Neuronpedia

    INDEX
    Explanations

    code elements like numbers and certain punctuation marks

    oai_token-act-pair · gemini-2.0-flash

    Brackets and colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.71
     Italijanski
    -0.64
    Autoritní
    -0.56
     >=",
    -0.56
     TextAppearance
    -0.55
     vermelhas
    -0.54
    ysacchar
    -0.54
    IndentedString
    -0.54
    IsMutable
    -0.54
     semej
    -0.54
    POSITIVE LOGITS
    YEN
    0.54
    IsContent
    0.47
     provincial
    0.47
    ydon
    0.44
    клопе
    0.44
    CreateInfo
    0.43
    ("*");
    0.42
    lide
    0.42
    zub
    0.42
     isInitialized
    0.42
    Act Density 0.192%

    No Known Activations