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

    Neuronpedia

    INDEX
    Explanations

    width and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     женщин
    0.38
     femelles
    0.38
    пион
    0.37
     பெண்கள்
    0.37
     tượng
    0.37
     Smoky
    0.36
    Zie
    0.36
    ktan
    0.35
     मादा
    0.35
     महिलाओ
    0.35
    POSITIVE LOGITS
     width
    0.48
     horizontal
    0.48
     horizontally
    0.44
     horizontale
    0.43
     chord
    0.42
    chord
    0.42
     hor
    0.42
     her
    0.41
     husband
    0.41
    Chord
    0.39
    Act Density 0.077%

    No Known Activations