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

    Neuronpedia

    INDEX
    Explanations

    autocorrelation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     misled
    1.10
    녠
    1.05
     hastily
    1.05
     MRD
    1.05
     AOL
    1.04
     聞い
    1.01
     GX
    1.00
     MDL
    0.99
     dehuman
    0.98
     disdain
    0.97
    POSITIVE LOGITS
    ि
    1.10
    ल
    0.95
    {"
    0.91
    ati
    0.91
    ید
    0.88
    يل
    0.88
    哪个
    0.86
    ème
    0.83
    ını
    0.83
    ılan
    0.83
    Act Density 0.001%

    No Known Activations