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

    Neuronpedia

    INDEX
    Explanations

    or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eduanya
    0.40
     auspicious
    0.39
    ക്കിയത്
    0.38
     टीस्पून
    0.38
     že
    0.38
    썹
    0.37
    💋
    0.37
    tuvo
    0.37
    ണമെന്ന്
    0.37
    etku
    0.36
    POSITIVE LOGITS
     или
    0.82
     veya
    0.73
    或其他
    0.71
     அல்லது
    0.71
     किंवा
    0.71
     hoặc
    0.70
    或
    0.70
     또는
    0.68
     અથવા
    0.66
     లేదా
    0.65
    Act Density 0.116%

    No Known Activations