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

    Neuronpedia

    INDEX
    Explanations

    printing output with arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ess
    0.47
    é
    0.46
    bé
    0.44
    ję
    0.41
    atis
    0.38
     때
    0.38
    ীব্র
    0.37
    nd
    0.36
    ang
    0.36
    bj
    0.36
    POSITIVE LOGITS
    他
    0.43
    炡
    0.43
    هن
    0.41
    ("
    0.40
    歡迎
    0.39
    ("^
    0.39
     foodie
    0.39
    MyLocation
    0.39
     ROUILLER
    0.39
    る
    0.39
    Act Density 0.061%

    No Known Activations