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

    Neuronpedia

    INDEX
    Explanations

    attachments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crime
    -0.07
     Conversion
    -0.06
     스
    -0.06
    /topics
    -0.06
    WHERE
    -0.06
     shown
    -0.06
    ωμα
    -0.06
    یدی
    -0.06
     permits
    -0.06
    _COLLECTION
    -0.06
    POSITIVE LOGITS
    .asarray
    0.07
    648
    0.07
    216
    0.06
    680
    0.06
    dag
    0.06
    ，大
    0.06
    (off
    0.06
    _EXTERN
    0.06
    208
    0.06
    320
    0.06
    Act Density 0.004%

    No Known Activations