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

    Neuronpedia

    INDEX
    Explanations

    foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.42
    và
    0.41
    of
    0.40
     धक्का
    0.40
    örg
    0.40
    curve
    0.39
    時は
    0.39
    carbonate
    0.38
    anday
    0.37
    naval
    0.37
    POSITIVE LOGITS
    ت
    0.72
    т
    0.68
    ר
    0.65
    त
    0.64
    ر
    0.57
    _
    0.57
    ла
    0.55
    י
    0.54
    র
    0.51
    ות
    0.50
    Act Density 0.024%

    No Known Activations