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

    Neuronpedia

    INDEX
    Explanations

    AI assistant refusing requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    РИ
    0.44
     senaste
    0.43
    丰富
    0.41
    疑惑
    0.40
     של
    0.40
     минера
    0.40
     антенна
    0.40
     із
    0.39
     لك
    0.38
     осве
    0.38
    POSITIVE LOGITS
     ataupun
    0.48
     அல்லது
    0.45
    however
    0.45
    However
    0.44
     or
    0.44
     However
    0.44
     however
    0.44
     अथवा
    0.43
     Jednak
    0.43
     কিংবা
    0.41
    Act Density 0.003%

    No Known Activations