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

    Neuronpedia

    INDEX
    Explanations

    phrases that enumerate examples, commonalities, or relationships between things

    oai_token-act-pair · gemini-2.0-flash

    generalizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XtraEditors
    -0.55
     sẻ
    -0.49
    Наводи
    -0.49
    anz
    -0.48
     uitges
    -0.47
    Kapcsolódó
    -0.46
    Atsauces
    -0.44
    īj
    -0.44
     Geografia
    -0.44
     yourselves
    -0.43
    POSITIVE LOGITS
    ConverterFactory
    0.56
    errHandler
    0.55
    ArgumentParser
    0.54
    InstanceState
    0.54
    Endian
    0.53
    SharedCtor
    0.50
    ItemLayout
    0.49
    usammen
    0.49
    pulo
    0.48
     useContext
    0.48
    Act Density 1.145%

    No Known Activations