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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _UNICODE
    -0.08
     ebony
    -0.08
    -media
    -0.07
     coastline
    -0.07
    VENTORY
    -0.07
    流星
    -0.07
     Ionic
    -0.07
    /us
    -0.06
    .epoch
    -0.06
    _banner
    -0.06
    POSITIVE LOGITS
     pragma
    0.07
    hu
    0.07
    ections
    0.07
    Au
    0.07
     Mag
    0.07
    any
    0.07
    !=
    0.07
    עניין
    0.07
    Wake
    0.07
    觉得很
    0.07
    Act Density 0.001%

    No Known Activations