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

    Neuronpedia

    INDEX
    Explanations

    code, legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amilton
    -0.08
    ambula
    -0.08
     colectivo
    -0.08
    profession
    -0.07
    ემ
    -0.07
    mele
    -0.07
     occupation
    -0.07
    occupation
    -0.07
    Occupation
    -0.07
    ၾက
    -0.07
    POSITIVE LOGITS
     won
    0.09
    	win
    0.09
     Win
    0.09
     Orn
    0.09
    WT
    0.09
     winning
    0.08
    Win
    0.08
    .functional
    0.08
    .metrics
    0.07
     বিজ
    0.07
    Act Density 0.001%

    No Known Activations