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

    Neuronpedia

    INDEX
    Explanations

    ready toaccount on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hobart
    1.19
     Saskatoon
    1.15
    backpack
    1.14
     Skate
    1.14
     Bradbury
    1.14
    اعة
    1.13
     Margot
    1.13
     McMaster
    1.12
    璞
    1.12
     SOAP
    1.12
    POSITIVE LOGITS
     N
    2.57
    N
    2.55
    Ns
    1.23
    NG
    1.20
     n
    1.18
     Н
    1.14
    n
    1.14
     M
    1.13
     K
    1.10
     G
    1.10
    Act Density 0.109%

    No Known Activations