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

    Neuronpedia

    INDEX
    Explanations

    about what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Padding
    0.51
     प्रोट
    0.49
     সঞ্জ
    0.49
     ViewHolder
    0.49
     Тол
    0.48
    пка
    0.48
     подготов
    0.47
     Де
    0.47
     дополнительных
    0.47
     Deportes
    0.47
    POSITIVE LOGITS
    dings
    0.46
    ]->
    0.44
    त्कार
    0.43
    stoke
    0.43
    stroke
    0.42
    eers
    0.41
    ায়ে
    0.41
     spook
    0.40
     sight
    0.39
     trap
    0.39
    Act Density 0.000%

    No Known Activations