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

    Neuronpedia

    INDEX
    Explanations

    systems and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emberek
    0.40
     largeur
    0.39
     tamaños
    0.39
    луйста
    0.38
     raies
    0.38
    度和
    0.38
    មើ
    0.37
     dónde
    0.37
     कीजिएगा
    0.37
     wherein
    0.37
    POSITIVE LOGITS
    ↵↵
    0.50
    。
    0.43
    ↵
    0.41
     (**
    0.40
    0.38
     Greenfield
    0.38
     Fintech
    0.38
    .
    0.37
    <unused2141>
    0.36
     This
    0.36
    Act Density 0.192%

    No Known Activations