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

    Neuronpedia

    INDEX
    Explanations

    strewn, litter, debris, shadows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    साठी
    0.54
    With
    0.52
     seseorang
    0.51
     satunya
    0.51
     \
    0.49
     રાશિફળ
    0.49
     With
    0.49
     PvP
    0.49
    ەیە
    0.49
    on
    0.48
    POSITIVE LOGITS
     debris
    0.59
    モ
    0.57
     strewn
    0.55
    根本
    0.53
    ន្ត
    0.53
    货物
    0.52
    垃圾
    0.52
    debris
    0.52
     ド
    0.52
     ਲੋ
    0.51
    Act Density 0.110%

    No Known Activations