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

    Neuronpedia

    INDEX
    Explanations

    photo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     textAlign
    0.94
     Haziran
    0.94
     tende
    0.92
     Hydrochloride
    0.91
    Ди
    0.90
    Ю
    0.89
    ృద్ధి
    0.88
    קות
    0.87
     Aynı
    0.86
     Bueno
    0.86
    POSITIVE LOGITS
    ą
    1.27
    да
    1.17
    na
    1.10
    dete
    1.05
    í
    1.04
    нің
    1.03
    sk
    0.97
    datos
    0.96
    ala
    0.94
    putes
    0.94
    Act Density 0.093%

    No Known Activations