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

    Neuronpedia

    INDEX
    Explanations

    heart of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    um
    1.55
     internacionales
    1.45
    if
    1.42
    ou
    1.36
    ro
    1.35
     bajar
    1.32
    í
    1.32
    iv
    1.28
    ip
    1.27
     fatores
    1.25
    POSITIVE LOGITS
    మైన
    1.34
    ﺵ
    1.33
    рена
    1.24
     copi
    1.20
    σή
    1.19
     outliers
    1.18
    कडून
    1.15
     inan
    1.13
    験
    1.12
     dữ
    1.11
    Act Density 0.119%

    No Known Activations