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

    Neuronpedia

    INDEX
    Explanations

    spring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.32
    是
    1.25
    и
    1.20
    ро
    1.17
    ла
    1.09
    і
    1.06
    ре
    1.05
    िंग
    1.02
    ри
    0.99
    ı
    0.99
    POSITIVE LOGITS
     I
    1.57
     Spring
    1.13
    Spring
    1.13
    SPRING
    1.13
    y
    0.96
     SPRING
    0.95
     Chub
    0.95
    ر
    0.93
     spring
    0.92
    К
    0.92
    Act Density 0.007%

    No Known Activations