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

    Neuronpedia

    INDEX
    Explanations

    vs or vs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     όχι
    0.42
     বলতে
    0.41
    გრამ
    0.40
     viszont
    0.39
     പറയാ
    0.38
    $)$.
    0.38
     unsubstituted
    0.38
    璈
    0.38
     ).
    0.37
     تھیں۔
    0.36
    POSITIVE LOGITS
     versus
    0.75
     vs
    0.67
     oppure
    0.64
    versus
    0.62
    vs
    0.60
     وبين
    0.58
     बनाम
    0.54
     VS
    0.54
    なのか
    0.52
     Versus
    0.49
    Act Density 0.361%

    No Known Activations