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

    Neuronpedia

    INDEX
    Explanations

    dark souls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arguments
    0.35
     argument
    0.35
     rotations
    0.34
     caches
    0.34
     buf
    0.33
     classes
    0.32
     tumble
    0.32
     loaves
    0.32
     notions
    0.32
     vezi
    0.32
    POSITIVE LOGITS
    However
    0.46
     மீண்டும்
    0.45
     Jetzt
    0.43
    ற்போது
    0.43
    Now
    0.42
     Şimdi
    0.42
     Ancak
    0.42
    After
    0.41
     jedoch
    0.41
    now
    0.41
    Act Density 0.012%

    No Known Activations