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

    Neuronpedia

    INDEX
    Explanations

    operators and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trusses
    0.21
    ław
    0.20
    \})
    0.20
     emotes
    0.19
    नाथन
    0.19
    Gson
    0.19
    norr
    0.19
    pleClass
    0.19
    itability
    0.19
    wehr
    0.18
    POSITIVE LOGITS
     ;
    0.32
    and
    0.32
     {
    0.28
     &&
    0.27
     ,"
    0.25
     ("
    0.25
     =>
    0.24
    AND
    0.24
     /
    0.23
     />
    0.23
    Act Density 0.317%

    No Known Activations