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

    Neuronpedia

    INDEX
    Explanations

    text processing and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caspase
    0.84
    та
    0.77
    서는
    0.77
     Durand
    0.77
     incend
    0.74
     Faculdade
    0.74
     Дэ
    0.74
     Ó
    0.73
     investigaciones
    0.73
     Normand
    0.73
    POSITIVE LOGITS
    ib
    0.79
    any
    0.76
     ollut
    0.71
    ikal
    0.68
    ol
    0.67
    furniture
    0.67
    წიფ
    0.67
    وسع
    0.66
    ust
    0.66
    ij
    0.66
    Act Density 0.001%

    No Known Activations