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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and conjunctions in the text

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

    starting with user followed by code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.58
    ConstraintMaker
    -0.45
    endphp
    -0.44
     Audiodateien
    -0.42
    stdbool
    -0.39
    ölker
    -0.39
     Loew
    -0.38
     them
    -0.38
    dpa
    -0.38
    toPromise
    -0.38
    POSITIVE LOGITS
    verifyException
    0.59
    rungsseite
    0.57
     Италијани
    0.54
    parsedMessage
    0.47
    olverine
    0.47
    帖最后由
    0.46
    principalColumn
    0.46
    Архівовано
    0.44
     Administrativna
    0.44
    évaluateur
    0.44
    Act Density 0.000%

    No Known Activations