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

    Neuronpedia

    INDEX
    Explanations

    is known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ளை
    0.68
    arczy
    0.66
     ফেলেছেন
    0.64
     겁니다
    0.62
    齟
    0.61
    ायला
    0.60
     없
    0.60
    殚
    0.60
    ienz
    0.59
     suffit
    0.59
    POSITIVE LOGITS
     known
    4.54
    known
    4.22
     Known
    4.21
    Known
    4.14
     conocido
    3.80
     conhecido
    3.73
     conocida
    3.65
     conhecida
    3.62
     conocidos
    3.52
     извест
    3.35
    Act Density 0.882%

    No Known Activations