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
    <main
    -0.07
    _sample
    -0.07
     Tan
    -0.07
    ToDevice
    -0.06
    companies
    -0.06
     captains
    -0.06
    .Cloud
    -0.06
     spar
    -0.06
    꾹
    -0.06
     investigate
    -0.06
    POSITIVE LOGITS
    ozilla
    0.08
     periodo
    0.07
     MOST
    0.07
     plist
    0.07
     balls
    0.07
    .control
    0.07
    都能
    0.07
    滴
    0.07
    .widget
    0.07
    life
    0.07
    Act Density 0.001%

    No Known Activations