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

    Neuronpedia

    INDEX
    Explanations

    multiple choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     booze
    -0.07
    脸
    -0.07
    olute
    -0.06
    Arrange
    -0.06
    _HEL
    -0.06
    CLK
    -0.06
     сервер
    -0.06
    別
    -0.06
    久
    -0.06
     Leap
    -0.06
    POSITIVE LOGITS
    ollar
    0.07
    /">
    0.07
     Tas
    0.07
     XML
    0.07
     Wik
    0.06
    _%
    0.06
     Tk
    0.06
     Buddhism
    0.06
    osph
    0.06
     Gender
    0.06
    Act Density 0.014%

    No Known Activations