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

    Neuronpedia

    INDEX
    Explanations

    introductions, applications, and predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     করিনি
    0.25
     tubig
    0.25
     marcó
    0.24
    鸪
    0.23
    این
    0.23
    தியின்
    0.23
    英國
    0.23
     Eropa
    0.23
    িত্যক্ত
    0.23
     sufrió
    0.23
    POSITIVE LOGITS
    을
    0.36
    に
    0.32
    を
    0.31
    에
    0.31
    으로
    0.29
    で
    0.29
    の
    0.28
    이
    0.27
    が
    0.26
    ,
    0.26
    Act Density 0.012%

    No Known Activations