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

    Neuronpedia

    INDEX
    Explanations

    common names and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alchemy
    0.62
     Adaptive
    0.61
     Vine
    0.59
    WAN
    0.59
    Kyle
    0.58
     Agile
    0.58
     Kyle
    0.58
     TextInput
    0.57
     URL
    0.57
    Nest
    0.57
    POSITIVE LOGITS
    愤怒
    0.92
     hükü
    0.89
     kormány
    0.87
     dítě
    0.87
    homeini
    0.84
     Buhari
    0.84
     Bolsonaro
    0.82
     himself
    0.82
     ಅವರು
    0.82
     tartış
    0.81
    Act Density 0.049%

    No Known Activations