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

    Neuronpedia

    INDEX
    Explanations

    express or implied warranties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.00
    т
    0.81
    त
    0.75
    ب
    0.75
    ल
    0.70
    t
    0.69
    #
    0.69
    ר
    0.69
    ম
    0.67
    ת
    0.65
    POSITIVE LOGITS
    s
    0.91
    arat
    0.60
    ﻃ
    0.59
    では
    0.58
    parsers
    0.58
     먼저
    0.57
    8
    0.55
    7
    0.55
    ソ
    0.55
     સુ
    0.55
    Act Density 0.002%

    No Known Activations