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

    Neuronpedia

    INDEX
    Explanations

    inherently incapable or inferior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    workspaceFolder
    1.05
    الف
    1.04
     lẽ
    1.00
    ın
    1.00
     //<
    0.98
     hỏi
    0.97
    ționale
    0.97
     klad
    0.96
    ನದ
    0.96
    دهای
    0.95
    POSITIVE LOGITS
    im
    1.23
     civilized
    1.16
    ively
    1.13
     singular
    1.09
    etter
    1.08
     て
    1.07
     разработ
    1.01
     assistive
    1.01
    ä
    1.01
     indisc
    1.00
    Act Density 0.007%

    No Known Activations