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

    Neuronpedia

    INDEX
    Explanations

    words containing the suffix "logi" or related to XML

    oai_token-act-pair · gemini-2.0-flash

    logical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chrétienne
    -0.65
     Extent
    -0.63
    ydable
    -0.63
     élastique
    -0.62
     Redevelopment
    -0.60
     Ecosystems
    -0.59
     Esti
    -0.59
     vectorielle
    -0.59
    pecker
    -0.59
    stairs
    -0.59
    POSITIVE LOGITS
    <bos>
    0.85
    LookAnd
    0.67
    ⓧ
    0.64
     Meksiku
    0.58
     GenerationType
    0.53
     EconPapers
    0.53
    '));
    0.51
     kasarigan
    0.50
     ویکی‌پدی
    0.49
    SourceChecksum
    0.49
    Act Density 1.012%

    No Known Activations