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

    Neuronpedia

    INDEX
    Explanations

    competition leading to improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apagos
    1.22
    et
    1.20
     erkl
    1.13
    on
    1.13
    etop
    1.10
     gratu
    1.08
     কমিটির
    1.05
    arquia
    1.04
    𠃊
    1.03
    kker
    1.02
    POSITIVE LOGITS
    snippets
    1.08
    ifold
    0.99
    \]
    0.97
    richt
    0.96
    ulfill
    0.95
    не
    0.94
     വാർത്ത
    0.94
    ด์
    0.93
     whatnot
    0.93
    follower
    0.92
    Act Density 0.001%

    No Known Activations