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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation, especially related to matrix operations and linear algebra

    oai_token-act-pair · gemini-2.0-flash

    jx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
     otomatig
    -0.69
     OFDb
    -0.68
    ViewFeatures
    -0.65
    StructEnd
    -0.60
     BoxFit
    -0.59
    kháu
    -0.57
    httphttps
    -0.54
     NSError
    -0.53
     naturais
    -0.53
    POSITIVE LOGITS
    __*/
    0.52
     TestBed
    0.48
    NGL
    0.46
     latter
    0.46
    <bos>
    0.45
    ftime
    0.45
    Ārējās
    0.44
    Portail
    0.44
    Brainz
    0.44
     Hough
    0.44
    Act Density 2.379%

    No Known Activations