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

    Neuronpedia

    INDEX
    Explanations

    text from news articles, particularly those that cite sources and include dates and names.

    oai_token-act-pair · gemini-2.0-flash

    omb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.56
     hôtels
    -0.52
     hObject
    -0.52
    Sucesor
    -0.51
    GenerationType
    -0.50
    StructEnd
    -0.49
     שוליים
    -0.49
    complexContent
    -0.47
    -0.45
    httphttps
    -0.45
    POSITIVE LOGITS
    //
    0.50
     Diſ
    0.45
     fhort
    0.44
     beſt
    0.43
     Jefus
    0.42
     Eſ
    0.42
    EntryPoint
    0.41
     Chrift
    0.41
    cheinend
    0.41
     purpoſe
    0.40
    Act Density 20.302%

    No Known Activations