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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    483
    -0.06
    =tmp
    -0.06
    56
    -0.06
    _busy
    -0.06
     Priest
    -0.06
     BAT
    -0.05
    REFERENCES
    -0.05
    만원
    -0.05
     severe
    -0.05
     reactions
    -0.05
    POSITIVE LOGITS
    car
    0.07
    	type
    0.07
    ycles
    0.07
    bou
    0.07
    oblin
    0.07
     Орг
    0.07
    ерг
    0.06
    (Window
    0.06
    _static
    0.06
    摩
    0.06
    Act Density 0.002%

    No Known Activations