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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surgery
    -0.07
     entropy
    -0.07
     surgery
    -0.06
     PERMISSION
    -0.06
    _enabled
    -0.06
    ých
    -0.06
     polít
    -0.06
    uptools
    -0.06
    λέον
    -0.06
     successor
    -0.06
    POSITIVE LOGITS
     JACK
    0.08
     tableView
    0.07
     Rochester
    0.07
     vui
    0.07
    基金
    0.07
    .array
    0.07
     Workplace
    0.06
     Image
    0.06
    brain
    0.06
    _ms
    0.06
    Act Density 0.000%

    No Known Activations