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

    Neuronpedia

    INDEX
    Explanations

    lack of sufficiency or visibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    0.57
    ,
    0.54
     of
    0.53
     되
    0.51
    !
    0.51
    "
    0.49
     bolstering
    0.48
     rounds
    0.47
     chipping
    0.47
     workforce
    0.45
    POSITIVE LOGITS
     صہیونیت
    0.53
    ഴിഞ്ഞ
    0.52
    popupIsOpen
    0.52
    isVideo
    0.51
     kapital
    0.51
    ildiği
    0.51
     கிமு
    0.49
    穸
    0.48
    कृति
    0.47
    🇬
    0.47
    Act Density 0.000%

    No Known Activations