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

    Neuronpedia

    INDEX
    Explanations

    Revealing something, expose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    니아
    -0.07
    ıklı
    -0.07
     Surprise
    -0.07
     pz
    -0.06
    >()
    -0.06
     ліс
    -0.06
    ูช
    -0.06
     되는
    -0.06
     Lucia
    -0.06
     프리
    -0.06
    POSITIVE LOGITS
    ísk
    0.07
    	color
    0.06
     UIView
    0.06
     artwork
    0.06
    .credit
    0.06
    Unavailable
    0.06
     Go
    0.06
    úmero
    0.06
    398
    0.06
    148
    0.06
    Act Density 0.081%

    No Known Activations