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

    Neuronpedia

    INDEX
    Explanations

    * **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urbed
    0.46
    Hungarian
    0.44
     ಪಡೆಯ
    0.43
    得以
    0.43
     PHOT
    0.41
    AINLESS
    0.41
     充電
    0.41
     경
    0.41
     WORKS
    0.40
    EMON
    0.40
    POSITIVE LOGITS
     tasas
    0.55
    ంచెం
    0.48
    جمة
    0.48
     cosas
    0.45
    实话
    0.45
    يلات
    0.43
     talla
    0.42
     decisiones
    0.41
     encaps
    0.41
     clasific
    0.41
    Act Density 0.008%

    No Known Activations