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

    Neuronpedia

    INDEX
    Explanations

    Python class initializations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ='{$
    -0.07
    alysis
    -0.07
    _truth
    -0.07
     resposta
    -0.07
     yem
    -0.06
    723
    -0.06
     dai
    -0.06
    	th
    -0.06
    Requested
    -0.06
    Jud
    -0.06
    POSITIVE LOGITS
     '"';↵
    0.07
     j
    0.07
     standard
    0.06
     miễn
    0.06
    	cancel
    0.06
    حم
    0.06
     role
    0.06
    (coeff
    0.06
     ]
↵
    0.06
     business
    0.06
    Act Density 0.008%

    No Known Activations