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

    Neuronpedia

    INDEX
    Explanations

    proper noun prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iders
    -0.10
     Bris
    -0.10
     Lau
    -0.10
     Gui
    -0.09
     Dude
    -0.08
    ãģ¡ãģ¯
    -0.08
    ijing
    -0.08
    gree
    -0.08
    wechat
    -0.08
     rake
    -0.08
    POSITIVE LOGITS
    ische
    0.16
    isch
    0.14
    ischer
    0.12
    ischen
    0.12
     language
    0.12
    ìĿĺ
    0.11
     government
    0.11
    isches
    0.11
    lish
    0.11
    style
    0.10
    Act Density 0.043%

    No Known Activations