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

    Neuronpedia

    INDEX
    Explanations

    please know, understand, choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.35
     دیک
    0.34
    larının
    0.32
    ﻤ
    0.31
     инструк
    0.31
     busting
    0.30
    /
    0.30
    rasında
    0.30
    ミン
    0.30
     său
    0.29
    POSITIVE LOGITS
    на
    0.45
    is
    0.41
    ia
    0.39
    é
    0.38
    с
    0.38
    im
    0.38
    ad
    0.37
    us
    0.37
    ان
    0.35
    éz
    0.35
    Act Density 0.032%

    No Known Activations