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

    Neuronpedia

    INDEX
    Explanations

    only handles or therefore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TAR
    0.47
    CAB
    0.42
     cn
    0.42
     silicate
    0.42
     extr
    0.41
     chin
    0.40
     boil
    0.40
     CAB
    0.40
    ابعه
    0.40
     Eb
    0.40
    POSITIVE LOGITS
     (${
    0.43
     മാത്രമല്ല
    0.42
     በፍ
    0.42
     빠르게
    0.41
     관리
    0.40
     ಬು
    0.39
     ലി
    0.39
     سریع
    0.39
    アクション
    0.39
    fed
    0.38
    Act Density 0.001%

    No Known Activations