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

    Neuronpedia

    INDEX
    Explanations

    import Foundation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.79
     with
    0.79
     about
    0.79
    1
    0.79
    test
    0.78
    r
    0.76
     get
    0.75
    7
    0.74
    räume
    0.73
    ?
    0.72
    POSITIVE LOGITS
    🙏
    0.96
    ۲
    0.95
    ot
    0.85
     transmembrane
    0.85
     سیاسی
    0.84
     لمبے
    0.82
    are
    0.82
     disini
    0.81
    🙏🙏
    0.80
    ການ
    0.80
    Act Density 0.000%

    No Known Activations