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

    Neuronpedia

    INDEX
    Explanations

    specific conditions or issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     floors
    0.42
    $
    0.41
     treaties
    0.40
     фак
    0.40
    華
    0.39
     fabric
    0.39
    circa
    0.39
    fact
    0.39
    房
    0.39
     mái
    0.38
    POSITIVE LOGITS
     PUC
    0.46
     Regul
    0.45
     حمله
    0.44
     القاعدة
    0.44
     ఆరోగ
    0.43
     NEGLIGENCE
    0.43
     Heterocycl
    0.43
    istung
    0.42
     ໜອງ
    0.42
    可以看出
    0.42
    Act Density 0.006%

    No Known Activations