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

    Neuronpedia

    INDEX
    Explanations

    refusal even with concessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ሜ
    0.47
     जानकारियां
    0.46
     ئێ
    0.45
     剤
    0.44
    囡
    0.44
     মৃত্য
    0.43
    亠
    0.42
    牷
    0.42
     جميعا
    0.42
     ที
    0.42
    POSITIVE LOGITS
    the
    0.49
    k
    0.48
     khi
    0.44
    <0x80>
    0.44
     might
    0.41
     con
    0.41
     inverso
    0.41
    raised
    0.41
     hyperglycemia
    0.40
     when
    0.40
    Act Density 0.001%

    No Known Activations