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

    Neuronpedia

    INDEX
    Explanations

    prices and signals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Github
    -0.08
    守
    -0.07
    _GRA
    -0.06
     UIWindow
    -0.06
    ToggleButton
    -0.06
     Manuals
    -0.06
     dovol
    -0.06
    也是
    -0.06
     Isaiah
    -0.06
    手に
    -0.06
    POSITIVE LOGITS
     nói
    0.07
     tweets
    0.06
    _logic
    0.06
    (datas
    0.06
    adolu
    0.06
    agent
    0.06
    .sock
    0.06
     incentive
    0.06
     carrot
    0.06
    Executable
    0.06
    Act Density 0.105%

    No Known Activations