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

    Neuronpedia

    INDEX
    Explanations

    kh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Achie
    -0.06
     Berk
    -0.06
     billionaire
    -0.06
     stato
    -0.06
     Parsing
    -0.06
    _USE
    -0.06
     sider
    -0.06
     Held
    -0.06
    _SCREEN
    -0.06
    	full
    -0.06
    POSITIVE LOGITS
    .Controls
    0.07
     тысяч
    0.06
     yüzyıl
    0.06
     Orwell
    0.06
    аны
    0.06
     příprav
    0.06
    보내기
    0.06
     emoc
    0.06
     DONE
    0.06
    列
    0.06
    Act Density 0.027%

    No Known Activations