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

    Neuronpedia

    INDEX
    Explanations

    center of relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    žev
    0.87
     conductas
    0.85
    aua
    0.83
     violación
    0.83
     VPD
    0.79
    גים
    0.79
     AirPods
    0.78
     Giac
    0.78
     gå
    0.77
     prendas
    0.76
    POSITIVE LOGITS
     center
    2.74
    center
    2.61
     centre
    2.58
     Center
    2.52
    Center
    2.50
     centers
    2.48
     centro
    2.39
    centre
    2.36
    Centre
    2.33
     Centre
    2.26
    Act Density 0.283%

    No Known Activations