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

    Neuronpedia

    INDEX
    Explanations

    -treated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    attacks
    -0.06
    bindings
    -0.06
    (cx
    -0.06
    IRS
    -0.06
     blade
    -0.06
     웹
    -0.06
    oncé
    -0.06
     Clyde
    -0.06
    арх
    -0.06
     mapping
    -0.06
    POSITIVE LOGITS
     若要
    0.07
    .FileOutputStream
    0.07
     hakk
    0.07
     Covered
    0.06
    ?></
    0.06
    Rib
    0.06
     Veg
    0.06
    -treated
    0.06
     viable
    0.06
     Чем
    0.06
    Act Density 0.014%

    No Known Activations