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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and expressions of doubt or disbelief

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

    hypothetical conditions or preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aşağı
    -0.35
    ge
    -0.35
    IsContent
    -0.34
    wiki
    -0.32
     Schluß
    -0.32
    berdayakan
    -0.30
     způso
    -0.30
    짝
    -0.30
     recuer
    -0.30
    os
    -0.30
    POSITIVE LOGITS
    uxxxx
    0.61
     AssemblyCompany
    0.61
     isNameExpr
    0.60
    VYMaps
    0.59
     itſelf
    0.59
     EconPapers
    0.58
     Anſ
    0.56
     myſelf
    0.56
     $_"
    0.56
    __;
    0.54
    Act Density 0.108%

    No Known Activations