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

    Neuronpedia

    INDEX
    Explanations

    preventing price increases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    නය
    0.46
    ан
    0.46
    شانی
    0.46
    ິນ
    0.45
     Bởi
    0.44
     طریقہ
    0.42
    ாடு
    0.42
     bức
    0.41
    仕組み
    0.41
    اداس
    0.41
    POSITIVE LOGITS
     into
    0.54
     defin
    0.50
     except
    0.50
    est
    0.50
    except
    0.48
     defini
    0.46
    2
    0.45
     in
    0.45
     back
    0.45
     that
    0.44
    Act Density 0.004%

    No Known Activations