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

    Neuronpedia

    INDEX
    Explanations

    Character descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     inadequate
    -0.07
     deficiency
    -0.07
     이것은
    -0.07
    民用
    -0.07
    一架
    -0.07
    상을
    -0.07
    .release
    -0.06
    적으로
    -0.06
     doença
    -0.06
    POSITIVE LOGITS
     dessert
    0.07
    gfx
    0.07
     Politico
    0.07
    _enemy
    0.07
    Options
    0.07
     trendy
    0.07
    公章
    0.07
    locked
    0.07
    �
    0.06
     Courts
    0.06
    Act Density 0.131%

    No Known Activations