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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ниже
    -0.07
     тим
    -0.07
    localized
    -0.06
    ignite
    -0.06
    )}>
    -0.06
    _prior
    -0.06
     merges
    -0.06
    omers
    -0.06
    	with
    -0.06
    してい
    -0.06
    POSITIVE LOGITS
    ppy
    0.07
    scar
    0.06
     ardından
    0.06
    (up
    0.06
     quir
    0.06
    NSE
    0.06
     embassy
    0.06
     PLUGIN
    0.06
     Kapoor
    0.06
     ку
    0.06
    Act Density 0.002%

    No Known Activations