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

    Neuronpedia

    INDEX
    Explanations

    punctuation and emphasis marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.49
     você
    0.49
    ათ
    0.44
    capitalize
    0.43
    ablement
    0.43
     tokoh
    0.42
    不超过
    0.41
     bạn
    0.40
     पण
    0.40
     उसकी
    0.40
    POSITIVE LOGITS
     era
    0.48
     Plant
    0.45
     gegründet
    0.44
    ^{-
    0.44
     CMV
    0.43
     Era
    0.43
     ஆண்டு
    0.42
     MDL
    0.42
    szág
    0.42
     Lun
    0.42
    Act Density 0.001%

    No Known Activations