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

    Neuronpedia

    INDEX
    Explanations

    workers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udas
    -0.07
     mg
    -0.07
     lig
    -0.07
    depart
    -0.07
    Videos
    -0.07
    -reference
    -0.07
    _band
    -0.06
     exp
    -0.06
     Spending
    -0.06
    [Z
    -0.06
    POSITIVE LOGITS
    лика
    0.07
    LOWER
    0.07
    airo
    0.06
     شكل
    0.06
    álním
    0.06
     něj
    0.06
    문화
    0.06
    	throw
    0.06
    Atlantic
    0.05
    是一个
    0.05
    Act Density 0.014%

    No Known Activations