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

    Neuronpedia

    INDEX
    Explanations

    physical impact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Media
    -0.08
     piled
    -0.07
    enda
    -0.06
     Cumberland
    -0.06
    	contentPane
    -0.06
     작품
    -0.06
    алів
    -0.06
     dobu
    -0.06
     logistics
    -0.06
    porno
    -0.06
    POSITIVE LOGITS
     個
    0.07
    Hosting
    0.07
     glow
    0.06
     turn
    0.06
     ハ
    0.06
     Usually
    0.06
    previous
    0.06
     moderators
    0.06
     sque
    0.06
     competitor
    0.06
    Act Density 0.060%

    No Known Activations