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

    Neuronpedia

    INDEX
    Explanations

    beta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    queryParams
    -0.07
    zos
    -0.06
    Parameter
    -0.06
    _scale
    -0.06
    .EOF
    -0.06
     luk
    -0.06
     desk
    -0.06
    _LOW
    -0.06
     Bunny
    -0.06
     ayr
    -0.06
    POSITIVE LOGITS
     سنة
    0.07
     voi
    0.07
    ancements
    0.06
     catering
    0.06
    *****
↵
    0.06
     entitled
    0.06
     Fon
    0.06
     таком
    0.06
    リング
    0.06
     такі
    0.06
    Act Density 0.019%

    No Known Activations