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

    Neuronpedia

    INDEX
    Explanations

    en variant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nack
    -0.07
     railways
    -0.07
     öff
    -0.07
    驶
    -0.07
    seek
    -0.06
    癸
    -0.06
    acs
    -0.06
    abstractmethod
    -0.06
     الشريف
    -0.06
    不锈
    -0.06
    POSITIVE LOGITS
    力争
    0.07
    (media
    0.07
    -fat
    0.07
    Portland
    0.07
     qa
    0.07
    headline
    0.07
    _VARIABLE
    0.06
    itat
    0.06
    regular
    0.06
     Forced
    0.06
    Act Density 0.001%

    No Known Activations