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

    Neuronpedia

    INDEX
    Explanations

    about followed by a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ز
    1.06
    ج
    1.00
    ف
    0.94
    ك
    0.90
    unk
    0.89
    ’’
    0.86
    CATEG
    0.83
    ش
    0.82
    দি
    0.79
    }`}
    0.79
    POSITIVE LOGITS
    ました
    1.42
     essendo
    1.38
    ましたが
    1.26
    ますが
    1.26
    lari
    1.20
    lardan
    1.20
     vibhav
    1.19
    스는
    1.18
    larini
    1.15
    Entonces
    1.15
    Act Density 0.132%

    No Known Activations