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

    Neuronpedia

    INDEX
    Explanations

    lists of characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ETTE
    0.40
     ಹೀ
    0.40
     yaptık
    0.40
     pubescence
    0.39
    mise
    0.38
     போன்ற
    0.38
     เงี้ย
    0.37
    噱
    0.37
     مما
    0.37
    ancellor
    0.37
    POSITIVE LOGITS
     listed
    0.71
     list
    0.52
    listed
    0.52
     contenders
    0.51
    เหล่านี้
    0.51
    Listed
    0.50
     Listed
    0.50
    List
    0.49
     below
    0.49
     список
    0.47
    Act Density 0.133%

    No Known Activations