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

    Neuronpedia

    INDEX
    Explanations

    time column metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ug
    0.84
     dua
    0.81
     bars
    0.79
     limiter
    0.79
     charity
    0.77
    ice
    0.77
    يه
    0.77
    ્ર
    0.77
     tombol
    0.76
    أ
    0.75
    POSITIVE LOGITS
    кры
    0.97
     asesin
    0.96
     vehículos
    0.88
     силы
    0.88
     расположены
    0.86
     указыва
    0.84
     сообщил
    0.83
     actuales
    0.82
     зарегистри
    0.82
    сных
    0.82
    Act Density 0.002%

    No Known Activations