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

    Neuronpedia

    INDEX
    Explanations

    Legal briefs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vì
    -0.08
    LIN
    -0.07
    享
    -0.07
     安
    -0.07
     예
    -0.07
    Explorer
    -0.06
     κα
    -0.06
    学会
    -0.06
    \Abstract
    -0.06
     languages
    -0.06
    POSITIVE LOGITS
     dul
    0.06
     lungs
    0.06
     Zy
    0.06
    >Z
    0.06
    	active
    0.06
    ivo
    0.06
    	se
    0.06
    .PostMapping
    0.06
     teal
    0.06
    IVO
    0.06
    Act Density 0.005%

    No Known Activations