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

    Neuronpedia

    INDEX
    Explanations

    ggplot geom_ elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    0.64
    정과
    0.57
    رت
    0.54
    kannya
    0.54
    rarr
    0.53
    지와
    0.53
    isterschaft
    0.52
     পরই
    0.52
    澄清
    0.52
    僧
    0.51
    POSITIVE LOGITS
     ส
    0.67
     الانت
    0.64
     polynomials
    0.62
     acteur
    0.62
     ethnic
    0.61
     ribosomes
    0.60
     이벤트
    0.60
     athletics
    0.59
    ANG
    0.58
     อ
    0.57
    Act Density 0.000%

    No Known Activations