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

    Neuronpedia

    INDEX
    Explanations

    web links with www

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐻
    0.77
    ணும்
    0.76
     করিব
    0.72
    hme
    0.70
     tecnolog
    0.69
     ファッション
    0.68
    ും
    0.67
     சுய
    0.67
    дел
    0.67
    考える
    0.66
    POSITIVE LOGITS
     राज्यसभा
    0.55
    aito
    0.54
    СТО
    0.54
     clinics
    0.54
    ⑸
    0.53
    станции
    0.52
     clínica
    0.52
    сто
    0.52
     والی
    0.51
     itching
    0.51
    Act Density 0.044%

    No Known Activations