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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters indicating structure in the text

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

    Code, math, or identifiers

    np_acts-logits-general · gemini-2.0-flash

    than, linear, tip structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aman
    -0.80
     McGovern
    -0.70
    Aman
    -0.70
     Gat
    -0.66
     Kog
    -0.63
     Carver
    -0.62
     Harrison
    -0.62
    Harrison
    -0.62
    \{\\
    -0.60
     Kot
    -0.60
    POSITIVE LOGITS
     Hyman
    0.78
     Faj
    0.76
     RS
    0.76
    df
    0.73
     Julien
    0.73
     rainbow
    0.71
    RS
    0.71
     df
    0.71
     Ced
    0.69
     TUL
    0.69
    Act Density 0.760%

    No Known Activations