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

    Neuronpedia

    INDEX
    Explanations

    words related to awards and recognition

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

    years after city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.47
    جغرافيا
    -0.41
    <!--
    -0.39
    WindowConstants
    -0.39
    ArgsConstructor
    -0.38
    dbh
    -0.36
     TestBed
    -0.36
    payers
    -0.36
    RTLR
    -0.36
    kozások
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.48
    rawDesc
    0.47
     évêque
    0.47
     îna
    0.46
     Erwä
    0.44
     ngoại
    0.43
    inerario
    0.42
     stepfather
    0.42
    parsedMessage
    0.42
     userSchema
    0.42
    Act Density 0.191%

    No Known Activations