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

    Neuronpedia

    INDEX
    Explanations

    there can be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     didn
    0.46
    ana
    0.44
    दोस्तों
    0.43
    had
    0.43
    ep
    0.42
     had
    0.41
     gave
    0.40
    s
    0.40
    experience
    0.40
     us
    0.39
    POSITIVE LOGITS
    នៃ
    0.52
    ของการ
    0.48
    ן
    0.46
    ﻟ
    0.45
    ל
    0.43
     simultaneous
    0.41
    stargo
    0.40
    的分
    0.40
     textural
    0.40
    <0xF3>
    0.39
    Act Density 0.004%

    No Known Activations