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

    Neuronpedia

    INDEX
    Explanations

    dual listed concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ！
    0.74
    !
    0.73
    ！！
    0.72
    esehatan
    0.68
     кстати
    0.64
    chiha
    0.64
     dyslex
    0.63
     Insulin
    0.63
    ampionship
    0.63
     lumbar
    0.62
    POSITIVE LOGITS
    -,
    1.18
    ,
    1.08
    -
    1.02
     &
    1.00
    ;
    0.96
     via
    0.93
    ”;
    0.93
    +,
    0.93
    .");
    0.90
    -/
    0.90
    Act Density 0.019%

    No Known Activations