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

    Neuronpedia

    INDEX
    Explanations

    data and information explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حين
    0.41
     नुकसान
    0.40
    มัน
    0.40
     गुणनखंड
    0.40
    ASE
    0.39
     കാരണ
    0.39
    cenie
    0.39
     trudno
    0.38
     تاکید
    0.38
     ની
    0.38
    POSITIVE LOGITS
     racially
    0.41
     ойнотуу
    0.40
     teas
    0.39
    श्त
    0.38
     металли
    0.38
    ივ
    0.38
     filtered
    0.38
    phins
    0.38
    erar
    0.38
    ಡುವ
    0.38
    Act Density 0.000%

    No Known Activations