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

    Neuronpedia

    INDEX
    Explanations

    legal theories, Python Packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AMPL
    0.47
    calend
    0.45
     anniversary
    0.45
     mapper
    0.43
     tolerances
    0.42
     namespaces
    0.42
    هاي
    0.41
    nesses
    0.41
     annivers
    0.40
     locale
    0.40
    POSITIVE LOGITS
     subjug
    0.52
     Vielzahl
    0.45
    وٹی
    0.44
     venge
    0.44
     subversive
    0.44
    ulpt
    0.43
     smug
    0.42
     disdain
    0.42
     shameless
    0.42
     disgust
    0.41
    Act Density 0.002%

    No Known Activations