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

    Neuronpedia

    INDEX
    Explanations

    symmetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    တွေ
    -0.08
    (params
    -0.08
     Pace
    -0.07
     disagreements
    -0.07
    arel
    -0.07
     પુસ્ત
    -0.07
     librarians
    -0.07
    /book
    -0.07
     Qualifications
    -0.07
    authorize
    -0.07
    POSITIVE LOGITS
    .CENTER
    0.10
    -axis
    0.10
     noon
    0.09
    中心
    0.09
    .Center
    0.08
     midpoint
    0.08
     rios
    0.08
     waterways
    0.08
     nws
    0.08
     airflow
    0.08
    Act Density 0.013%

    No Known Activations