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

    Neuronpedia

    INDEX
    Explanations

    parts of a research paper that describe a scientific experiment in detail, especially with equations and discussion of results

    oai_token-act-pair · gemini-2.0-flash

    labels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SwingConstants
    -0.53
    NameInMap
    -0.52
    }());
    -0.49
    IsInitialized
    -0.47
    ObjectContext
    -0.47
    spreading
    -0.46
    iprot
    -0.44
    EnumMember
    -0.44
     spreading
    -0.44
    וויק
    -0.44
    POSITIVE LOGITS
     Labels
    0.73
     labels
    0.73
    LABEL
    0.64
    labels
    0.63
     truth
    0.63
     true
    0.62
     label
    0.62
    出版年
    0.62
     Label
    0.62
     Truths
    0.61
    Act Density 3.458%

    No Known Activations