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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     You
    1.37
     For
    1.36
     Make
    1.34
     Aug
    1.29
     För
    1.28
     \#
    1.26
     Don
    1.25
     Avoid
    1.24
     Coordinate
    1.23
     Can
    1.23
    POSITIVE LOGITS
     household
    0.89
     industry
    0.87
     world
    0.87
     news
    0.86
     beverage
    0.83
     headphone
    0.82
     home
    0.82
    the
    0.81
     restauration
    0.81
     meeting
    0.81
    Act Density 0.023%

    No Known Activations