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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new section or paragraph in the text

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

    Tokens after "Q:"

    np_acts-logits-general · gemini-2.0-flash

    lots of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.63
    Alike
    -0.53
    τως
    -0.51
    AndEndTag
    -0.51
    digde
    -0.49
     illet
    -0.48
    ,:),
    -0.45
     gev
    -0.45
    ulemon
    -0.45
    cac
    -0.45
    POSITIVE LOGITS
    AxisAlignment
    0.56
     ہی
    0.56
     ही
    0.52
     autorytatywna
    0.52
    DJANGO
    0.50
    usammen
    0.50
    MemoryWarning
    0.49
    UrlResolution
    0.48
    leftarrow
    0.48
    úsqueda
    0.48
    Act Density 0.016%

    No Known Activations