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

    Neuronpedia

    INDEX
    Explanations

    logical or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ದೇಹ
    0.35
     thyroid
    0.32
    自身の
    0.31
     cathode
    0.31
     tube
    0.31
     Aids
    0.31
    記錄
    0.31
    ട്ടില്ല
    0.30
    とその
    0.30
     Kết
    0.30
    POSITIVE LOGITS
     veya
    0.66
     অথবা
    0.63
     или
    0.62
     અથવા
    0.61
     அல்லது
    0.59
     లేదా
    0.53
     किंवा
    0.52
     ولكن
    0.52
     ಅಥವಾ
    0.51
    หรือ
    0.51
    Act Density 0.000%

    No Known Activations