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

    Neuronpedia

    INDEX
    Explanations

    difficult time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.41
    ği
    1.30
     obsol
    1.26
    Granted
    1.24
    $)$.
    1.23
     tế
    1.21
    ]));
    1.18
     joys
    1.18
     वडील
    1.18
    复制代码
    1.16
    POSITIVE LOGITS
    е
    1.57
    ੀਆਂ
    1.47
    ्रांत
    1.46
     Quels
    1.41
    ো
    1.38
     Illness
    1.37
    ことになる
    1.34
    इयों
    1.32
    рый
    1.29
     عنها
    1.27
    Act Density 0.017%

    No Known Activations