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

    Neuronpedia

    INDEX
    Explanations

    development store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    訶
    0.39
    composer
    0.38
     изображение
    0.37
     આવ્યો
    0.36
     quarter
    0.36
    ोटो
    0.36
    Berry
    0.35
    quarter
    0.34
    carbam
    0.34
    0.34
    POSITIVE LOGITS
     placed
    0.42
    Placed
    0.41
    ριθ
    0.40
    placed
    0.39
     빈
    0.39
     advertised
    0.39
    .”)
    0.38
    龊
    0.37
    舞蹈
    0.37
    ம்பெ
    0.36
    Act Density 0.000%

    No Known Activations