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

    Neuronpedia

    INDEX
    Explanations

    numerical data and citations related to research studies

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

    Numbers followed by punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    24 followed by text/symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocino
    -0.61
    LError
    -0.52
    حياتها
    -0.48
     trefoil
    -0.46
    füh
    -0.45
    いれば
    -0.44
    erialize
    -0.43
    fileId
    -0.43
    BeforeMethod
    -0.43
    حياته
    -0.42
    POSITIVE LOGITS
    حوالہ
    0.60
    Zal
    0.57
     GenerationType
    0.54
     Zal
    0.54
     Tasmanian
    0.52
    二十四
    0.52
     cuantas
    0.52
     Nast
    0.50
    Nast
    0.50
    GEBURTSDATUM
    0.49
    Act Density 0.783%

    No Known Activations