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

    Neuronpedia

    INDEX
    Explanations

    is and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ct
    -0.07
     remove
    -0.06
     пан
    -0.06
     Cary
    -0.06
    Toy
    -0.06
     assaults
    -0.06
     Hart
    -0.06
    Deletes
    -0.06
    SERVICE
    -0.06
    Video
    -0.06
    POSITIVE LOGITS
     bilir
    0.07
     تواند
    0.06
    GRAM
    0.06
    ograf
    0.06
     jlong
    0.06
    /pl
    0.06
    abbage
    0.06
    础
    0.06
    asticsearch
    0.06
    $o
    0.06
    Act Density 0.006%

    No Known Activations