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

    Neuronpedia

    INDEX
    Explanations

    elements related to data processing and data manipulation commands

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

    Data between "<write>" and "</write>"

    np_acts-logits-general · gemini-2.0-flash

    geometric mean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobalSection
    -0.56
     asiatique
    -0.53
     murale
    -0.52
     refunded
    -0.52
    fortawesome
    -0.51
     Coronel
    -0.51
     isNameExpr
    -0.50
    Kinda
    -0.50
    protoc
    -0.50
    انيف
    -0.50
    POSITIVE LOGITS
    crose
    0.61
     tartalomajánló
    0.61
     burn
    0.61
     May
    0.59
    出版年
    0.58
    نگار
    0.58
    taza
    0.57
     Turnbull
    0.57
    RefreshLayout
    0.57
    pulumi
    0.57
    Act Density 1.516%

    No Known Activations