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

    Neuronpedia

    INDEX
    Explanations

    model response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。【
    0.97
    ①
    0.97
     ①
    0.94
    ^{'
    0.93
    '=>$
    0.92
    ...');
    0.92
     ちゃっ
    0.91
     আরো
    0.90
     newspapers
    0.89
     '[
    0.89
    POSITIVE LOGITS
     ни
    0.69
     Ribbon
    0.65
     Exile
    0.64
     вибра
    0.62
    Steady
    0.60
     ды
    0.60
     RIP
    0.60
     gef
    0.60
     बेल
    0.58
     зу
    0.57
    Act Density 0.172%

    No Known Activations