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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hockey
    -0.06
    _classes
    -0.06
     land
    -0.06
     tracks
    -0.06
    教授
    -0.06
    ('('
    -0.06
    ใส
    -0.06
     Content
    -0.06
    開発
    -0.06
     submarines
    -0.06
    POSITIVE LOGITS
    inalg
    0.06
    afort
    0.06
     Hond
    0.06
    aille
    0.06
     pang
    0.06
     Partisi
    0.06
    372
    0.06
    /em
    0.06
    "g
    0.06
    uly
    0.06
    Act Density 0.002%

    No Known Activations