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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons and measurements

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

    greater than, smaller than, lower than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Література
    -0.48
    曖昧さ回避
    -0.48
     Administrativna
    -0.48
    ArgsConstructor
    -0.47
     Италијани
    -0.46
     שוליים
    -0.46
    MarshalTo
    -0.45
     vors
    -0.45
     Wicidata
    -0.44
    +#+#
    -0.43
    POSITIVE LOGITS
     سكانية
    0.43
     produkcji
    0.40
     HFILL
    0.35
     оригіналу
    0.34
     الحره
    0.33
    queles
    0.33
     Produced
    0.32
    Produced
    0.32
     produção
    0.32
     langsung
    0.31
    Act Density 0.150%

    No Known Activations