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

    Neuronpedia

    INDEX
    Explanations

    transition words or phrases that introduce additional information or summarize

    oai_token-act-pair · gemini-2.0-flash

    Furthermore/Moreover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.78
     Sado
    -0.54
     ***!
    -0.54
    ContentAsync
    -0.49
     Италијани
    -0.49
    ↵
    -0.49
    Personensuche
    -0.47
    Mouse
    -0.47
    featureID
    -0.47
     وتسجيلات
    -0.47
    POSITIVE LOGITS
     fermée
    0.63
     InputDecoration
    0.57
    CppMethod
    0.56
    MemoryWarning
    0.54
    GeneratedMessage
    0.53
    CloseOperation
    0.52
     dévelo
    0.51
     fermés
    0.51
     picioare
    0.50
    IFICATE
    0.50
    Act Density 0.298%

    No Known Activations