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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocy
    -0.07
     cx
    -0.06
     врач
    -0.06
     goat
    -0.06
    िथ
    -0.06
     condom
    -0.06
    자를
    -0.06
    Mo
    -0.06
     presents
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    )");↵
    0.07
     *);↵↵
    0.07
    .includes
    0.06
    原始
    0.06
     NSLocalizedString
    0.06
    .'
    0.06
    .skill
    0.06
     Makes
    0.06
    )');↵
    0.06
    Logging
    0.06
    Act Density 0.076%

    No Known Activations