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

    Neuronpedia

    INDEX
    Explanations

    making assumptions with data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مث
    0.55
     scarc
    0.52
    រ
    0.50
    𖥔
    0.47
     кла
    0.47
    <bbox>
    0.46
     मार
    0.46
    બસ
    0.46
    穰
    0.46
     зак
    0.46
    POSITIVE LOGITS
     dispersed
    0.49
     network
    0.46
    UInteger
    0.45
     mixed
    0.45
     gold
    0.44
    edia
    0.42
     reconstructed
    0.42
     weight
    0.41
    ，
    0.41
    Gu
    0.41
    Act Density 0.002%

    No Known Activations