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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biomarker
    0.48
    ônia
    0.47
    นี่
    0.46
     asla
    0.46
     günler
    0.45
     login
    0.42
     diameter
    0.41
    これが
    0.41
    ílio
    0.41
     weekends
    0.41
    POSITIVE LOGITS
    ፏ
    0.50
    出一
    0.48
    νη
    0.46
    了一
    0.45
    ց
    0.45
     [*
    0.44
     Consideration
    0.41
    免疫
    0.41
     ως
    0.41
    疥
    0.41
    Act Density 0.013%

    No Known Activations