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

    Neuronpedia

    INDEX
    Explanations

    categorized breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    larımız
    1.03
    ्स
    1.01
    𝕣
    0.96
    㛺
    0.93
     Horoscope
    0.89
     curbing
    0.88
    ાઇલ
    0.88
     Personally
    0.87
    $("#
    0.86
     llegada
    0.86
    POSITIVE LOGITS
    en
    1.28
    er
    1.06
    ch
    0.94
    ak
    0.90
    fo
    0.85
    enian
    0.84
    ques
    0.82
    n
    0.81
    nama
    0.81
     той
    0.80
    Act Density 0.174%

    No Known Activations