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

    Neuronpedia

    INDEX
    Explanations

    list items or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !).
    0.91
    !),
    0.88
    !)
    0.87
    !]
    0.84
    )!
    0.82
    !);
    0.82
     haha
    0.78
     😂
    0.78
    !");
    0.78
     !)
    0.76
    POSITIVE LOGITS
    IMENTAL
    0.64
    Environmental
    0.64
     способствует
    0.63
    ুঁ
    0.61
     Аль
    0.60
    লায়
    0.59
     Олимпий
    0.58
    Strategies
    0.57
    Contributor
    0.57
    Laptop
    0.57
    Act Density 0.139%

    No Known Activations