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

    Neuronpedia

    INDEX
    Explanations

    message, master, Keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আসা
    0.41
     ಎಷ್ಟು
    0.41
    چہ
    0.40
    筚
    0.37
    Bezier
    0.37
    जनन
    0.36
    在哪里
    0.36
    }}^{*}\
    0.36
    িল্লি
    0.36
    msqrt
    0.35
    POSITIVE LOGITS
    टी
    0.39
     autoc
    0.34
    трен
    0.33
    ту
    0.33
     Lafayette
    0.33
     ad
    0.33
    item
    0.33
    тего
    0.33
     исто
    0.33
     EV
    0.32
    Act Density 0.000%

    No Known Activations