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

    Neuronpedia

    INDEX
    Explanations

    information within academic citations, especially URLs and bracketed information.

    oai_token-act-pair · gemini-2.0-flash

    research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.66
    Autoritní
    -0.64
    Chham
    -0.63
    BeginInit
    -0.63
     TextAlign
    -0.58
    참고
    -0.57
    InvalidProtocol
    -0.57
     <>",
    -0.57
     الرياضيه
    -0.57
     referenties
    -0.57
    POSITIVE LOGITS
     صوتيه
    0.46
     system
    0.44
    ///</
    0.43
    System
    0.42
    Dining
    0.42
    \{\\
    0.42
     Dining
    0.41
     gela
    0.40
     dining
    0.40
     amor
    0.40
    Act Density 5.822%

    No Known Activations