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

    Neuronpedia

    INDEX
    Explanations

    Coding/technical contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abestanden
    -0.94
    NamedQueries
    -0.66
    OrBuilder
    -0.60
    endregion
    -0.59
     jScrollPane
    -0.58
    URLConnection
    -0.57
    ğinde
    -0.57
    例文帳に追加
    -0.56
    EndInit
    -0.55
    Rhestr
    -0.55
    POSITIVE LOGITS
     unknownFields
    0.54
     hoạch
    0.52
     Anaconda
    0.49
     invokingState
    0.47
    hezza
    0.47
    invokeLater
    0.46
    ctuary
    0.46
     jadx
    0.46
     utilisation
    0.45
     fascination
    0.45
    Act Density 0.002%

    No Known Activations