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

    Neuronpedia

    INDEX
    Explanations

    lists sections or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     può
    0.40
     hiểu
    0.33
     şeyler
    0.33
     değildir
    0.33
     نہیں
    0.33
     compréhension
    0.32
     puede
    0.31
    وت
    0.31
     değil
    0.31
     monopolies
    0.31
    POSITIVE LOGITS
    その他の
    0.30
    ជាមួយនឹង
    0.30
    关于
    0.30
     использованием
    0.29
    に対する
    0.29
     사용하여
    0.29
     използ
    0.28
    Miscellaneous
    0.28
     기타
    0.27
    சிற
    0.27
    Act Density 0.061%

    No Known Activations