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

    Neuronpedia

    INDEX
    Explanations

    synthetic fibers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᴾ
    0.46
    🅐
    0.44
    歿
    0.43
    鍘
    0.43
     باوجود
    0.43
     Конечно
    0.43
    RAR
    0.42
    ದಿಂದ
    0.42
    肦
    0.42
    squre
    0.41
    POSITIVE LOGITS
     ap
    0.48
     more
    0.45
     fl
    0.44
     etc
    0.43
    j
    0.42
    x
    0.42
     tablecloth
    0.42
     Q
    0.42
    t
    0.41
     systemic
    0.40
    Act Density 0.001%

    No Known Activations