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

    Neuronpedia

    INDEX
    Explanations

    timing and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     collezione
    0.52
    ний
    0.50
    alley
    0.49
     городского
    0.47
    city
    0.46
    Cotton
    0.46
    ട്ടിയ
    0.45
    ol
    0.45
     دیگری
    0.45
    adze
    0.44
    POSITIVE LOGITS
    节
    0.43
     pores
    0.41
     panc
    0.41
     Concentration
    0.41
    ゚
    0.39
     sleeves
    0.39
     capaz
    0.39
     eer
    0.39
     ack
    0.39
     oxid
    0.38
    Act Density 0.001%

    No Known Activations