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

    Neuronpedia

    INDEX
    Explanations

    pairing nouns with descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    1.43
    y
    1.37
    c
    1.35
     it
    1.28
    it
    1.28
    b
    1.22
    h
    1.21
    at
    1.17
    u
    1.17
    in
    1.15
    POSITIVE LOGITS
     ಮತ್ತು
    1.24
    ът
    1.23
    ＆
    1.20
    Л
    1.15
     Tecnología
    1.15
     மற்றும்
    1.14
     Vý
    1.13
    Х
    1.12
    ቴክ
    1.11
     régionale
    1.11
    Act Density 0.000%

    No Known Activations