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

    Neuronpedia

    INDEX
    Explanations

    Chrome Web Store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asi
    0.96
    пли
    0.95
    ли
    0.89
    ла
    0.87
     Parigi
    0.82
    の手
    0.82
    な
    0.81
    рата
    0.80
    си
    0.80
    ل
    0.80
    POSITIVE LOGITS
    }{
    0.84
     bylo
    0.84
    leetcode
    0.78
     احتم
    0.78
    exhaustive
    0.78
     bluff
    0.77
    iense
    0.77
     hedges
    0.77
     ugly
    0.77
     intolerable
    0.77
    Act Density 0.005%

    No Known Activations