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

    Neuronpedia

    INDEX
    Explanations

    mathematical and alphanumeric symbols and expressions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ÐIJÑĢÑħÑĸв
    -0.10
     {}".
    -0.07
     //!<
    -0.07
     {}'.
    -0.07
    <UnityEngine
    -0.07
    /by
    -0.07
    Âłmi
    -0.07
     XCT
    -0.06
    ulet
    -0.06
     {}",
    -0.06
    POSITIVE LOGITS
     _,
    0.07
    oning
    0.07
     (
    0.07
    æĸ¹éĿ¢
    0.07
    ober
    0.06
     vs
    0.06
    را
    0.06
     же
    0.06
     mn
    0.06
    .*,
    0.06
    Act Density 0.552%

    No Known Activations