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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンダ
    -0.08
    워
    -0.08
    hp
    -0.08
    abases
    -0.07
     prol
    -0.07
     apex
    -0.07
    dept
    -0.07
     setback
    -0.07
    comes
    -0.07
     comprises
    -0.07
    POSITIVE LOGITS
     использование
    0.09
     أنك
    0.08
     IH
    0.08
     обеспечение
    0.08
     توفير
    0.08
     znale
    0.08
    การ
    0.08
     создание
    0.08
     اینکه
    0.08
     mob
    0.07
    Act Density 0.134%

    No Known Activations