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

    Neuronpedia

    INDEX
    Explanations

    if you'd like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     large
    0.37
     Hãy
    0.36
     x
    0.32
     skulle
    0.31
     veya
    0.31
     në
    0.31
     असल्यास
    0.30
     least
    0.30
     خواهد
    0.30
     الض
    0.30
    POSITIVE LOGITS
     it
    0.71
    佢
    0.55
    它
    0.55
     you
    0.52
     он
    0.52
     הוא
    0.49
    you
    0.48
    это
    0.48
     It
    0.47
     его
    0.47
    Act Density 0.108%

    No Known Activations