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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly names

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

    Middle Eastern names

    np_acts-logits-general · gemini-2.0-flash

    Abdul and Abdel names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    []):
    -0.54
    агности
    -0.47
    batore
    -0.46
    cin
    -0.44
    DeleteBehavior
    -0.44
    AnchorStyles
    -0.43
    Up
    -0.43
     up
    -0.43
    ग
    -0.42
    зон
    -0.42
    POSITIVE LOGITS
     nakalista
    0.68
    MENAFN
    0.67
    Filmographie
    0.63
    InstanceState
    0.63
    WriteBarrier
    0.59
     ddelweddau
    0.58
    LookAnd
    0.58
     surla
    0.58
    SourceChecksum
    0.56
    errHandler
    0.56
    Act Density 0.414%

    No Known Activations