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

    Neuronpedia

    INDEX
    Explanations

    *Adjusts*, *Holds*, *her*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ংকে
    0.45
    ник
    0.44
    দক্ষ
    0.43
     adapta
    0.38
     равно
    0.38
     csak
    0.38
     আটকে
    0.38
    摀
    0.38
    ضع
    0.38
    छि
    0.38
    POSITIVE LOGITS
    ূপ
    0.37
    angal
    0.36
    dominal
    0.35
    ibirsk
    0.35
    蛋
    0.35
    owo
    0.34
    뎀
    0.34
    itares
    0.34
     pizzas
    0.34
    dorff
    0.33
    Act Density 0.002%

    No Known Activations