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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _budget
    -0.06
     reproduced
    -0.06
     cá
    -0.06
     foss
    -0.06
     petits
    -0.06
    -scale
    -0.06
     Peter
    -0.06
     khá
    -0.06
    .Accept
    -0.06
     intend
    -0.06
    POSITIVE LOGITS
     licenses
    0.07
     shutdown
    0.07
    FieldValue
    0.06
    XX
    0.06
    xx
    0.06
    于
    0.06
     Также
    0.06
    Role
    0.06
     acquisitions
    0.06
     UnityEditor
    0.06
    Act Density 0.000%

    No Known Activations