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

    Neuronpedia

    INDEX
    Explanations

    .,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    埕
    -0.07
    沂
    -0.07
    误会
    -0.07
     Introduced
    -0.07
     indis
    -0.07
     homicide
    -0.07
    主席
    -0.07
    晨
    -0.06
     ContentView
    -0.06
     hurdle
    -0.06
    POSITIVE LOGITS
    abajo
    0.07
    WEEN
    0.07
    ulos
    0.06
     tekn
    0.06
    OGLE
    0.06
     assert
    0.06
    ding
    0.06
    ималь
    0.06
    .dataset
    0.06
    0.06
    Act Density 0.013%

    No Known Activations