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

    Neuronpedia

    INDEX
    Explanations

    here or there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doubt
    1.05
     duda
    0.96
     заключается
    0.95
     dúvida
    0.90
     nyeri
    0.89
     wordt
    0.83
    ન્મ
    0.83
     judi
    0.82
     wonder
    0.82
    سرائيل
    0.82
    POSITIVE LOGITS
     everytime
    0.86
    เพราะ
    0.70
    because
    0.67
     потому
    0.66
    Dist
    0.66
     নিক
    0.65
     Потому
    0.65
     because
    0.65
     لأن
    0.63
     whereas
    0.62
    Act Density 0.009%

    No Known Activations