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

    Neuronpedia

    INDEX
    Explanations

    programming imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heresy
    0.57
     mitral
    0.51
     sympath
    0.48
     mensch
    0.48
     opio
    0.48
     opium
    0.47
     inhum
    0.45
     domande
    0.44
     leichte
    0.44
    צו
    0.44
    POSITIVE LOGITS
    );
    0.48
     Visibility
    0.47
     Revenue
    0.47
     Sub
    0.46
     It
    0.46
     Payments
    0.45
     другой
    0.45
    Sub
    0.44
     Payment
    0.44
     Similar
    0.44
    Act Density 0.002%

    No Known Activations