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

    Neuronpedia

    INDEX
    Explanations

    * , 6 , ** , <start_of_turn>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ewną
    0.46
     Vorteil
    0.45
    رمین
    0.44
     lợi
    0.43
    iapan
    0.43
    ramento
    0.42
    alagi
    0.41
     advantage
    0.41
     bộ
    0.41
    اک
    0.40
    POSITIVE LOGITS
    ខ្ញុំ
    0.43
    ത്യ
    0.40
    Parallel
    0.40
     زي
    0.39
    يدا
    0.39
     Parallel
    0.39
    ECs
    0.39
    ప
    0.39
    艦
    0.38
    ﾈ
    0.38
    Act Density 0.006%

    No Known Activations