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

    Neuronpedia

    INDEX
    Explanations

    Website user interaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olding
    -0.07
    ét
    -0.07
    measurement
    -0.07
     STATIC
    -0.06
     assessment
    -0.06
    atische
    -0.06
     deposition
    -0.06
     appraisal
    -0.06
    IND
    -0.06
    irectory
    -0.06
    POSITIVE LOGITS
     उसन
    0.07
     özelliği
    0.06
     unsus
    0.06
     aydın
    0.06
    (unique
    0.06
     많은
    0.06
    ของร
    0.06
     若要
    0.06
    Conexion
    0.06
    _FETCH
    0.06
    Act Density 0.097%

    No Known Activations