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

    Neuronpedia

    INDEX
    Explanations

    focus and commitment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     разобра
    1.00
    ק
    0.98
     bystanders
    0.93
    した
    0.92
     IndexPath
    0.92
     отмети
    0.89
    账
    0.88
    ωσε
    0.87
     вот
    0.87
    hoot
    0.87
    POSITIVE LOGITS
    dont
    1.05
     dioxide
    1.03
    Thời
    0.97
    Toxic
    0.92
    dh
    0.90
     dove
    0.89
    дары
    0.87
    Tiempo
    0.86
    seas
    0.86
    PackageManager
    0.85
    Act Density 0.129%

    No Known Activations