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

    Neuronpedia

    INDEX
    Explanations

    ICO and related offerings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮏ
    0.60
     kiến
    0.56
     equilíbrio
    0.56
    嘊
    0.55
     WPARAM
    0.53
     ơn
    0.52
     sırasında
    0.51
     MTLTexture
    0.51
     silly
    0.51
    ہے
    0.50
    POSITIVE LOGITS
    db
    0.70
     with
    0.67
    c
    0.64
    data
    0.63
     با
    0.62
    als
    0.61
    va
    0.61
    ID
    0.60
    count
    0.59
    fue
    0.59
    Act Density 0.002%

    No Known Activations