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

    Neuronpedia

    INDEX
    Explanations

    commands and requests related to input processing or data management

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

    instructions and directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Architekt
    -0.38
     ریزی
    -0.38
    árbol
    -0.37
    Билгалдахарш
    -0.37
    CloseOperation
    -0.37
    GIVEREF
    -0.36
    ColumnHeaders
    -0.36
    RTHOOK
    -0.36
     hendak
    -0.35
     pauv
    -0.35
    POSITIVE LOGITS
    évaluateur
    0.46
    saraba
    0.46
     Cæsar
    0.44
    InSection
    0.40
    EndGlobalSection
    0.40
     StatelessWidget
    0.40
     transférez
    0.39
     Chbosky
    0.39
    pdp
    0.39
    gemini
    0.38
    Act Density 0.190%

    No Known Activations