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

    Neuronpedia

    INDEX
    Explanations

    levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gesch
    -0.07
    WISE
    -0.07
    oub
    -0.07
    íš
    -0.06
    _resp
    -0.06
    Css
    -0.06
    ращения
    -0.06
    cih
    -0.06
    (validate
    -0.06
     نوشته
    -0.06
    POSITIVE LOGITS
    ifestyles
    0.07
    +'"
    0.06
     Harley
    0.06
     regs
    0.06
    -move
    0.06
    ैं।↵
    0.06
     SEN
    0.06
     언
    0.06
     progressives
    0.06
    axter
    0.06
    Act Density 0.019%

    No Known Activations