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

    Neuronpedia

    INDEX
    Explanations

    else blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glimpse
    0.83
    iénd
    0.83
     Далее
    0.78
    rafo
    0.77
    ʀ
    0.77
    তে
    0.76
     また
    0.76
    𝘀
    0.75
     abnormally
    0.73
    राशि
    0.73
    POSITIVE LOGITS
    en
    0.81
    р
    0.75
    Д
    0.71
    Notre
    0.70
    j
    0.69
     kaut
    0.68
    wast
    0.66
    צו
    0.66
    En
    0.66
    Am
    0.65
    Act Density 0.008%

    No Known Activations