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

    Neuronpedia

    INDEX
    Explanations

    namespace App

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hvor
    0.45
    wisdom
    0.43
     where
    0.42
     pierws
    0.41
    NEA
    0.40
    benef
    0.40
    hala
    0.40
     där
    0.39
    $
    0.39
    \"
    0.39
    POSITIVE LOGITS
     mermaid
    0.46
     shorthand
    0.43
     Transportation
    0.43
    লিখিত
    0.42
     Label
    0.42
     transportation
    0.42
     mouthpiece
    0.42
     Wechsel
    0.41
     shorth
    0.41
     sensation
    0.41
    Act Density 0.000%

    No Known Activations