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

    Neuronpedia

    INDEX
    Explanations

    computational terms and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حتی
    0.46
    furniture
    0.43
    H
    0.43
    ;
    0.42
    অ
    0.41
    kut
    0.40
    intestinal
    0.39
    hhh
    0.39
    a
    0.39
    inflammation
    0.39
    POSITIVE LOGITS
     Byte
    0.49
     byte
    0.44
     měl
    0.42
     брат
    0.42
     Bytes
    0.42
     Hersteller
    0.41
     Dél
    0.40
     grandchild
    0.40
     Sonu
    0.38
     CharPtr
    0.38
    Act Density 1.133%

    No Known Activations