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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -private
    -0.06
    驚
    -0.06
    enia
    -0.06
    _lc
    -0.06
     Cyc
    -0.06
    .om
    -0.06
    	pub
    -0.06
     bureauc
    -0.06
    テレビ
    -0.06
     peaceful
    -0.06
    POSITIVE LOGITS
     percentage
    0.07
    식
    0.06
    astically
    0.06
    portion
    0.06
     최신
    0.06
    anchor
    0.06
     onComplete
    0.06
    itant
    0.06
     scholarship
    0.06
     knack
    0.06
    Act Density 0.003%

    No Known Activations