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

    Neuronpedia

    INDEX
    Explanations

    javascript function documentation annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.33
     mengak
    1.31
    ೊ
    1.30
    eluarkan
    1.24
    ubwa
    1.24
    तुरंग
    1.23
    த்
    1.22
     arrayOf
    1.21
    ور
    1.20
    వి
    1.18
    POSITIVE LOGITS
    щик
    1.32
    st
    1.16
    е
    1.11
    𝚍
    1.04
    rar
    1.02
    浮か
    1.00
    sth
    1.00
    sthe
    0.99
    дели
    0.97
    его
    0.97
    Act Density 0.001%

    No Known Activations