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

    Neuronpedia

    INDEX
    Explanations

    the presence of colons and related punctuation

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

    Smiley face punctuation

    np_acts-logits-general · gemini-2.0-flash

    expressive emoji endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.90
    aarrggbb
    -0.89
    +#+#
    -0.70
     SEDS
    -0.67
     Ressources
    -0.67
    keyColumn
    -0.67
    enumi
    -0.67
    #
    -0.66
    AndEndTag
    -0.65
    таратура
    -0.65
    POSITIVE LOGITS
    D
    0.70
    P
    0.64
    wink
    0.55
    O
    0.51
    rolley
    0.51
    o
    0.51
     )
    0.49
    bige
    0.49
    -\
    0.49
    -}
    0.49
    Act Density 0.094%

    No Known Activations