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

    Neuronpedia

    INDEX
    Explanations

    dw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Speaking
    -0.07
    models
    -0.07
     develop
    -0.07
     serum
    -0.06
    Game
    -0.06
    Texto
    -0.06
    된다
    -0.06
    Deaths
    -0.06
     commanded
    -0.06
    _dy
    -0.06
    POSITIVE LOGITS
    OfString
    0.06
     cheeks
    0.06
    adin
    0.06
     поперед
    0.06
     Mercedes
    0.06
    ：↵
    0.06
     ',↵
    0.06
     selon
    0.06
     ΕΛ
    0.06
     '{$
    0.06
    Act Density 0.002%

    No Known Activations