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

    Neuronpedia

    INDEX
    Explanations

    UK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मर्ज
    0.38
     bổ
    0.37
    png
    0.36
     verde
    0.36
     Với
    0.36
    Defocused
    0.35
     Dus
    0.35
     hő
    0.35
     دس
    0.35
     DSM
    0.34
    POSITIVE LOGITS
     unpre
    0.38
    囯
    0.37
    }}_{\
    0.36
     محفوظة
    0.36
     ['(?
    0.36
     effortless
    0.35
    调
    0.35
    ילו
    0.35
    䖝
    0.35
    ViewById
    0.35
    Act Density 0.003%

    No Known Activations