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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     круп
    -0.07
     Ekim
    -0.06
    exampleModal
    -0.06
    @index
    -0.06
    prop
    -0.06
    .dropout
    -0.06
    _Item
    -0.06
    obierno
    -0.06
    iqué
    -0.06
     primero
    -0.06
    POSITIVE LOGITS
    iaux
    0.06
    ';
↵
↵
    0.06
    /';↵↵
    0.06
     Sail
    0.06
    touches
    0.06
     Hell
    0.06
     Yugosl
    0.06
    rebbe
    0.06
    gz
    0.06
    }"↵↵
    0.06
    Act Density 0.004%

    No Known Activations