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

    Neuronpedia

    INDEX
    Explanations

    kingdoms and kings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    檚
    1.55
    시켜
    1.50
    ோருக்கு
    1.45
    情况下
    1.40
     движения
    1.38
    \!\
    1.36
    _-
    1.35
    azaki
    1.35
     thirds
    1.34
    𝘬
    1.33
    POSITIVE LOGITS
    wide
    1.80
    se
    1.73
     fom
    1.60
    تم
    1.52
    oltre
    1.52
    नैतिक
    1.46
    ﻌ
    1.46
    getTotal
    1.44
    ꜰ
    1.43
     Cerc
    1.43
    Act Density 0.112%

    No Known Activations