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

    Neuronpedia

    INDEX
    Explanations

    references to people and their roles or relationships in various contexts

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

    before proper nouns/names

    np_acts-logits-general · gemini-2.0-flash

    academy graduate Scott

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ariel
    -0.53
     mof
    -0.50
    <-
    -0.50
    tich
    -0.48
     retire
    -0.47
    略歴
    -0.46
    ่วย
    -0.46
    ovia
    -0.45
     PAPERS
    -0.45
    getClass
    -0.45
    POSITIVE LOGITS
    WireFormatLite
    0.83
    #+#
    0.76
     Callum
    0.67
    expandindo
    0.67
    aarrggbb
    0.66
    Personensuche
    0.65
     kaarangay
    0.65
    oneofs
    0.65
    windowFixed
    0.65
    contentLoaded
    0.65
    Act Density 0.099%

    No Known Activations