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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лей
    -0.07
    resp
    -0.07
     dois
    -0.07
    %',↵
    -0.06
    _so
    -0.06
    лок
    -0.06
    ˆ
    -0.06
    ∅
    -0.06
    chrome
    -0.06
    door
    -0.06
    POSITIVE LOGITS
    אוו
    0.08
    برشلون
    0.07
    产学
    0.07
     AFF
    0.07
     Vander
    0.07
    邸
    0.06
    詹姆
    0.06
    ModelAttribute
    0.06
     pickerView
    0.06
    _TB
    0.06
    Act Density 0.013%

    No Known Activations