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

    Neuronpedia

    INDEX
    Explanations

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ERAL
    0.75
    此之外
    0.72
     sclerosis
    0.68
     گے
    0.66
     Homeless
    0.66
    UITableView
    0.66
    ɴ
    0.66
    iorari
    0.65
    خدم
    0.64
    andte
    0.64
    POSITIVE LOGITS
    人
    0.84
    م
    0.75
    ରି
    0.75
    m
    0.71
    ज
    0.70
    𝐲
    0.70
    রা
    0.69
    oretically
    0.68
    ir
    0.68
    স
    0.67
    Act Density 0.020%

    No Known Activations