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

    Neuronpedia

    INDEX
    Explanations

    electrons moving and interacting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Elect
    0.85
    Electronic
    0.84
    Elect
    0.83
     Electronic
    0.81
     élect
    0.80
    Elekt
    0.77
     Elekt
    0.74
     электро
    0.73
     ηλεκ
    0.72
    Electro
    0.72
    POSITIVE LOGITS
     società
    0.43
     xã
    0.42
     positioned
    0.40
     singularity
    0.40
     reaching
    0.39
     champagne
    0.38
     pul
    0.38
     bioc
    0.38
     silhouettes
    0.37
     shrinking
    0.37
    Act Density 0.004%

    No Known Activations