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

    Neuronpedia

    INDEX
    Explanations

    of interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    1.64
    р
    1.57
    𝚝
    1.52
     zerstört
    1.37
     echt
    1.34
     hohen
    1.33
    ﺍ
    1.29
    Bước
    1.27
    مان
    1.27
    ﻴ
    1.27
    POSITIVE LOGITS
    ך
    1.42
    NESS
    1.41
    1.36
    1.34
    1.31
    daki
    1.30
    ע
    1.30
    ↵↵
    1.27
    ს
    1.23
    ش
    1.23
    Act Density 0.007%

    No Known Activations