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

    Neuronpedia

    INDEX
    Explanations

    words related to valves, chambers, the state of being closed, and actions being controlled

    oai_token-act-pair · gemini-2.0-flash

    closed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     closed
    -2.58
     Closed
    -2.23
    closed
    -2.22
    Closed
    -2.11
     CLOSED
    -1.91
     closing
    -1.87
     closure
    -1.82
     closes
    -1.81
     Closing
    -1.76
    Closing
    -1.69
    POSITIVE LOGITS
    ]--;
    0.67
     betweenstory
    0.65
    fjspx
    0.60
    \}\\
    0.54
    haviors
    0.53
     estekak
    0.52
    AutoScaleMode
    0.51
    awaiter
    0.51
    ########.
    0.50
     ddelweddau
    0.50
    Act Density 8.791%

    No Known Activations