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

    Neuronpedia

    INDEX
    Explanations

    categorical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     locations
    -0.07
    도록
    -0.07
     квітня
    -0.07
     に
    -0.07
     yılda
    -0.07
    [val
    -0.07
    .ToDouble
    -0.07
    254
    -0.07
    经济
    -0.06
    venue
    -0.06
    POSITIVE LOGITS
    _terms
    0.07
     imaginative
    0.07
     categorical
    0.07
    ymbols
    0.06
    刑
    0.06
     COMMENTS
    0.06
    、マ
    0.06
    openid
    0.06
    dart
    0.06
     Pascal
    0.06
    Act Density 0.003%

    No Known Activations