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

    Neuronpedia

    INDEX
    Explanations

    tokens starting with t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    皑
    0.47
     devolución
    0.43
    ាហ
    0.41
    แด
    0.40
     ray
    0.39
     জাহান
    0.39
     Um
    0.39
    ıştır
    0.39
    inko
    0.38
    umus
    0.38
    POSITIVE LOGITS
    تمي
    0.45
     t
    0.41
    τώ
    0.38
    trunc
    0.38
     tendance
    0.38
    Str
    0.38
     terminations
    0.37
     str
    0.36
    textit
    0.36
    str
    0.36
    Act Density 0.002%

    No Known Activations