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

    Neuronpedia

    INDEX
    Explanations

    pre-built packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лда
    0.72
    琭
    0.66
    эс
    0.65
    لان
    0.65
     Fond
    0.64
    lors
    0.63
    fond
    0.63
    wydd
    0.62
     नेताओं
    0.62
    Fond
    0.62
    POSITIVE LOGITS
     complete
    2.35
     package
    2.29
     Complete
    2.20
     packages
    2.15
    Complete
    2.13
     packaged
    2.09
    complete
    2.07
     Package
    1.99
     Packages
    1.90
     completa
    1.89
    Act Density 0.880%

    No Known Activations