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

    Neuronpedia

    INDEX
    Explanations

    ure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    찌
    -0.07
     knot
    -0.07
    (sort
    -0.07
    _commit
    -0.07
    	pass
    -0.07
    axios
    -0.07
    (buff
    -0.07
     atual
    -0.07
    茛
    -0.07
    动工
    -0.07
    POSITIVE LOGITS
     Yugoslavia
    0.08
    ereg
    0.08
    تعديل
    0.08
    'Re
    0.07
    气氛
    0.07
     ure
    0.07
     Osw
    0.07
     heterosexual
    0.07
    abcdefghijkl
    0.07
    च
    0.07
    Act Density 0.005%

    No Known Activations