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

    Neuronpedia

    INDEX
    Explanations

    tokenized strings or characters used in programming syntax

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

    regular expression syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.51
    AndEndTag
    -0.48
     kasarigan
    -0.48
    +#+
    -0.43
     Wikiseite
    -0.40
    ApiProperty
    -0.40
     colors
    -0.39
    Personensuche
    -0.39
     الرياضيه
    -0.38
    onedDateTime
    -0.38
    POSITIVE LOGITS
    ::_('
    0.54
     {}));
    0.49
    +:+
    0.48
    Accademia
    0.45
    endregion
    0.44
    ]=>
    0.41
    inaudible
    0.39
    lede
    0.39
    :");
    0.39
    Erstellt
    0.38
    Act Density 0.000%

    No Known Activations