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

    Neuronpedia

    INDEX
    Explanations

    shocked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mqtt
    -0.07
     пит
    -0.07
    顏
    -0.06
     stack
    -0.06
     항
    -0.06
    距離
    -0.06
    !↵↵↵↵
    -0.06
     flags
    -0.06
     buyer
    -0.06
     Baron
    -0.06
    POSITIVE LOGITS
    וחר
    0.08
     Osama
    0.07
    אוניברס
    0.07
    _experiment
    0.07
     форму
    0.07
    ując
    0.07
    OMB
    0.07
    ernes
    0.07
    чувств
    0.07
    Constructor
    0.07
    Act Density 0.338%

    No Known Activations