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

    Neuronpedia

    INDEX
    Explanations

    * after that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Berat
    0.44
    Stan
    0.41
    Ign
    0.41
    Pet
    0.41
    可能
    0.40
    Trigger
    0.39
    ء
    0.38
    Win
    0.38
    Grace
    0.38
    Weight
    0.38
    POSITIVE LOGITS
    ...”
    0.42
     សូម
    0.41
     কর্তব্য
    0.41
     calam
    0.41
     Сури
    0.40
    ຟ
    0.40
     receivables
    0.40
     }}}
    0.39
     substituent
    0.39
    aliana
    0.39
    Act Density 0.000%

    No Known Activations