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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __
    -0.52
     (
    -0.41
     simple
    -0.40
    ,
    -0.40
    _
    -0.39
    log
    -0.38
    __*/
    -0.37
    ers
    -0.37
    or
    -0.36
    /
    -0.36
    POSITIVE LOGITS
     الحره
    0.94
     الرياضيه
    0.91
    )";
    0.91
    )");
    0.90
    parsedMessage
    0.84
     actionMode
    0.82
    )"),
    0.82
    ")"
    0.82
    PerformLayout
    0.81
    ſelf
    0.80
    Act Density 0.066%

    No Known Activations