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

    Neuronpedia

    INDEX
    Explanations

    .Drawing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _controls
    -0.06
     SwiftUI
    -0.06
     Airport
    -0.06
    �
    -0.06
     Worlds
    -0.06
     Concert
    -0.06
     [],
↵
    -0.06
    __('
    -0.06
    soup
    -0.06
    @ResponseBody
    -0.06
    POSITIVE LOGITS
     land
    0.07
    cing
    0.07
    札
    0.07
    활동
    0.07
     Dancing
    0.07
    漢
    0.06
    enuous
    0.06
    омет
    0.06
     HOME
    0.06
    \"",↵
    0.06
    Act Density 0.001%

    No Known Activations