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

    Neuronpedia

    INDEX
    Explanations

    toxins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responseBody
    -0.06
    드리
    -0.06
    аче
    -0.06
    达
    -0.06
    =',
    -0.06
     Stub
    -0.06
    Moved
    -0.06
     Oy
    -0.06
     güney
    -0.06
    .DESC
    -0.06
    POSITIVE LOGITS
     toxins
    0.09
    敬
    0.07
    	unit
    0.07
     passwords
    0.07
    ۱۶
    0.07
     Zot
    0.07
     JOptionPane
    0.07
     oauth
    0.06
     làng
    0.06
    skin
    0.06
    Act Density 0.002%

    No Known Activations