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

    Neuronpedia

    INDEX
    Explanations

    programming keywords and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    2.33
    ا
    2.26
    ة
    2.19
    te
    2.10
    caya
    1.97
    (",");
    1.87
    ed
    1.84
    tion
    1.79
    tel
    1.77
    tamil
    1.76
    POSITIVE LOGITS
     importantly
    2.43
     जिम्मेदार
    2.18
     outp
    2.03
    bearing
    2.00
    かも
    1.99
     emplacement
    1.94
    ॒
    1.92
    öd
    1.90
     tā
    1.89
    ;;)
    1.89
    Act Density 0.070%

    No Known Activations