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

    Neuronpedia

    INDEX
    Explanations

    restless, floppy, nervous energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ামুটি
    1.10
     tolerances
    1.07
    ంచ్
    1.05
    fasst
    1.02
    ний
    1.01
     kullanılan
    0.98
    عية
    0.98
     dominions
    0.98
    owników
    0.98
    רים
    0.97
    POSITIVE LOGITS
    a
    1.70
    .
    1.37
    '
    1.34
    ی
    1.24
    an
    1.20
    o
    1.08
    e
    1.06
    u
    1.05
    _
    1.04
    ে
    1.03
    Act Density 0.276%

    No Known Activations