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

    Neuronpedia

    INDEX
    Explanations

    references to plans, proposals, and consideration of scenarios or projects

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

    evaluating options and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.67
     للاسماء
    -0.59
     ویکی‌پدی
    -0.50
     tóxic
    -0.49
    SourceChecksum
    -0.46
     ſind
    -0.45
    principalColumn
    -0.44
    ญิง
    -0.44
    ölkerung
    -0.44
     Infór
    -0.43
    POSITIVE LOGITS
    makeConstraints
    0.44
    FunctionFlags
    0.38
    mekte
    0.37
    evos
    0.35
     通販
    0.34
    esses
    0.34
    autique
    0.34
    lotten
    0.34
    statement
    0.33
    sud
    0.33
    Act Density 0.150%

    No Known Activations