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

    Neuronpedia

    INDEX
    Explanations

    listing items, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的には
    0.36
     असल्याने
    0.32
    므로
    0.32
    mittedly
    0.32
    すぎて
    0.31
     hänen
    0.31
    celikle
    0.31
    ಕ್ಕಿಂತ
    0.31
     westbound
    0.31
     femelle
    0.30
    POSITIVE LOGITS
     etc
    0.66
    等等
    0.66
     etcétera
    0.63
     등을
    0.60
     इत्यादी
    0.59
     প্রভৃতির
    0.59
     इत्यादि
    0.57
     тощо
    0.57
     등이
    0.55
     वगैरह
    0.55
    Act Density 0.341%

    No Known Activations