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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    body
    0.70
    one
    0.66
    Happy
    0.66
    {~
    0.65
    avil
    0.63
    im
    0.63
    ĥ
    0.63
    %(
    0.62
    Allowed
    0.62
    tikzpicture
    0.61
    POSITIVE LOGITS
     funcionalidades
    1.09
     proteínas
    1.02
     autoridades
    1.01
     prestaciones
    1.00
     enormes
    0.99
     ligados
    0.95
     diferenci
    0.94
     desempeñ
    0.93
     menores
    0.91
     normas
    0.91
    Act Density 0.001%

    No Known Activations