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

    Neuronpedia

    INDEX
    Explanations

    opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SOFTWARE
    -0.07
     khóa
    -0.07
     původ
    -0.06
    항
    -0.06
    quired
    -0.06
    	raw
    -0.06
     Fortune
    -0.06
     wav
    -0.06
     phải
    -0.06
     punto
    -0.06
    POSITIVE LOGITS
    _xy
    0.07
     yrs
    0.07
    [OF
    0.06
    ,[],
    0.06
     Eisenhower
    0.06
    ][_
    0.06
     ~~
    0.06
    0.06
    	HX
    0.06
    627
    0.06
    Act Density 0.058%

    No Known Activations