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

    Neuronpedia

    INDEX
    Explanations

    calendar invite names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idd
    0.43
    疹
    0.38
    न्ड
    0.37
    यान
    0.37
    ř
    0.37
    mayor
    0.37
    PCM
    0.36
    alfi
    0.36
    ைகளைப்
    0.36
    aj
    0.35
    POSITIVE LOGITS
     wiggle
    0.43
     songwriters
    0.37
    老虎
    0.37
     слуша
    0.37
     озеро
    0.37
     worrisome
    0.37
    худ
    0.36
     great
    0.36
     musically
    0.36
    лығы
    0.36
    Act Density 0.000%

    No Known Activations