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

    Neuronpedia

    INDEX
    Explanations

    positional encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ல்லை
    0.55
     bladder
    0.49
     pipette
    0.48
     technology
    0.46
    ہنی
    0.46
     isometric
    0.46
     stints
    0.46
     reservoir
    0.46
    ोत
    0.45
     gastronom
    0.45
    POSITIVE LOGITS
     "\"
    0.41
    垒
    0.39
    煥
    0.39
    null
    0.39
    ^{\
    0.38
    )?
    0.38
    étrico
    0.38
    わけ
    0.37
     いう
    0.37
    ቑ
    0.37
    Act Density 0.003%

    No Known Activations