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

    Neuronpedia

    INDEX
    Explanations

    Minority

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .c
    -0.08
    疥
    -0.07
    耽误
    -0.07
     경우에는
    -0.07
    ∶
    -0.07
     Teddy
    -0.07
    _COL
    -0.07
    _helper
    -0.06
    .getC
    -0.06
    願意
    -0.06
    POSITIVE LOGITS
    .mongodb
    0.08
     angered
    0.08
    学业
    0.07
    默
    0.07
     arts
    0.07
    ghan
    0.06
     przegl
    0.06
     outrage
    0.06
    пло
    0.06
    辘
    0.06
    Act Density 0.013%

    No Known Activations