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

    Neuronpedia

    INDEX
    Explanations

    identifiers and keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iteten
    0.96
    heastern
    0.95
    ｭ
    0.93
    一个月
    0.92
    OSED
    0.90
    ilmiştir
    0.87
    ிருக்கிறது
    0.87
    agrave
    0.86
    ivational
    0.86
    hitungan
    0.86
    POSITIVE LOGITS
     A
    1.13
    Attrs
    1.09
     Meski
    1.05
    芑
    1.05
     L
    1.04
     and
    1.02
     K
    1.01
    ค์
    1.01
     I
    1.00
    ة
    1.00
    Act Density 0.031%

    No Known Activations