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

    Neuronpedia

    INDEX
    Explanations

    references to datasets related to training and testing in machine learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    training data set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цездатний
    -0.71
    səhifə
    -0.67
    Tikang
    -0.60
    InitVars
    -0.60
     ब्रेकडाउन
    -0.59
    __(/*!
    -0.59
    verifyException
    -0.59
    期刊论文
    -0.59
    Бележки
    -0.58
    zeera
    -0.58
    POSITIVE LOGITS
     dataset
    0.44
     DataLoader
    0.43
     corpus
    0.39
    queryset
    0.39
    corpus
    0.37
     patrons
    0.34
     population
    0.33
     Dataset
    0.33
     training
    0.33
     samples
    0.33
    Act Density 0.022%

    No Known Activations