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

    Neuronpedia

    INDEX
    Explanations

    notable or prominent items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thermodynamics
    0.95
     Environmental
    0.89
     Probability
    0.87
     you
    0.86
     Assessing
    0.86
     on
    0.83
     that
    0.83
     jeopard
    0.83
     But
    0.82
     You
    0.82
    POSITIVE LOGITS
     prominently
    0.80
    Notable
    0.80
     notable
    0.71
    な
    0.71
    ようだ
    0.71
     prominent
    0.70
    дона
    0.70
     noticeable
    0.67
     noteworthy
    0.67
     homegrown
    0.66
    Act Density 0.073%

    No Known Activations