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

    Neuronpedia

    INDEX
    Explanations

    the word "connect" or variations thereof

    oai_token-act-pair · gemini-2.0-flash

    connect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    The
    -0.69
     
    -0.57
    '
    -0.57
     hendes
    -0.57
     meet
    -0.53
     The
    -0.52
    /
    -0.50
    <bos>
    -0.49
    P
    -0.49
    M
    -0.49
    POSITIVE LOGITS
    ViewImports
    1.04
    \{\\
    0.99
     doInBackground
    0.97
    XmlAccessType
    0.93
     Kenobi
    0.92
     AssemblyCulture
    0.91
    posedge
    0.91
     MainAxisSize
    0.90
    petrol
    0.89
     '\\;'
    0.88
    Act Density 2.219%

    No Known Activations