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

    Neuronpedia

    INDEX
    Explanations

    JSON objects and markup tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [
    0.77
     Even
    0.76
     •
    0.75
     (
    0.72
     set
    0.72
     (~
    0.72
     …
    0.70
     ~
    0.70
     (\
    0.69
     *
    0.69
    POSITIVE LOGITS
     Beruf
    0.83
     வருவத
    0.83
    ünü
    0.82
     potentialities
    0.82
     virtud
    0.81
    ۪
    0.79
    intai
    0.78
     सलामी
    0.78
     institution
    0.78
    0.78
    Act Density 0.387%

    No Known Activations