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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emann
    -0.07
    _scalar
    -0.07
     некоторые
    -0.06
    (expect
    -0.06
    -Star
    -0.06
     RouteServiceProvider
    -0.06
     '';↵↵
    -0.06
    -written
    -0.06
     ($("#
    -0.06
    iParam
    -0.06
    POSITIVE LOGITS
    atsby
    0.06
    HUD
    0.06
     creator
    0.06
     Caroline
    0.06
     charms
    0.06
    WB
    0.06
    Characters
    0.06
    (format
    0.06
     teeth
    0.06
     женщина
    0.05
    Act Density 0.272%

    No Known Activations