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

    Neuronpedia

    INDEX
    Explanations

    Great

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poems
    -0.08
    籍
    -0.08
     Floyd
    -0.08
     данный
    -0.08
     rw
    -0.07
     शामिल
    -0.07
    .transform
    -0.07
    ));
↵
    -0.07
    Jen
    -0.07
     escapes
    -0.07
    POSITIVE LOGITS
     progresso
    0.09
     بالنسبة
    0.09
     thanks
    0.08
     avances
    0.08
    .us
    0.08
     apparition
    0.08
     avanço
    0.08
     productive
    0.08
     апп
    0.08
     begitu
    0.07
    Act Density 0.021%

    No Known Activations