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

    Neuronpedia

    INDEX
    Explanations

    mathematical identity concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nisha
    0.45
    CrL
    0.45
     круп
    0.44
    姦
    0.41
     жүктөп
    0.40
    bedrooms
    0.40
    Despatx
    0.40
    鄔
    0.40
    妿
    0.39
     дра
    0.39
    POSITIVE LOGITS
     identity
    1.16
    Identity
    1.13
    identity
    1.07
     Identity
    1.03
     IDENTITY
    0.91
    IDENTITY
    0.89
     identidad
    0.87
    单位
    0.81
     identidade
    0.80
     unit
    0.79
    Act Density 0.021%

    No Known Activations