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

    Neuronpedia

    INDEX
    Explanations

    am programmed to refuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     भागों
    0.36
     μέρος
    0.35
    鑷
    0.35
     부분이
    0.34
    emar
    0.34
     ۋە
    0.33
     Baş
    0.32
    yyati
    0.32
    zada
    0.32
    emic
    0.32
    POSITIVE LOGITS
     constitution
    0.42
    簡易
    0.39
     miniatur
    0.39
     enable
    0.39
     easily
    0.38
     detector
    0.38
    例文帳に追加
    0.37
     例文帳に追加
    0.37
     সহজে
    0.37
    constitution
    0.37
    Act Density 0.000%

    No Known Activations