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

    Neuronpedia

    INDEX
    Explanations

    hollow structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.76
    $
    0.70
    il
    0.69
    EN
    0.67
    ES
    0.66
    一
    0.65
     as
    0.64
     for
    0.64
     or
    0.63
    0.62
    POSITIVE LOGITS
     quienes
    0.65
    ۔
    0.62
    ित
    0.61
    altered
    0.61
    ุน
    0.60
    seleccion
    0.59
     फेब्रुवारी
    0.59
     جنہوں
    0.58
    ん
    0.58
     जिन्होंने
    0.57
    Act Density 0.001%

    No Known Activations