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

    Neuronpedia

    INDEX
    Explanations

    career highlights and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.30
    ?
    1.12
     ,
    1.09
     That
    1.05
    ，
    1.00
    !
    0.96
     This
    0.94
     be
    0.93
     nosso
    0.93
     ،
    0.92
    POSITIVE LOGITS
    Altri
    1.09
    lerinden
    1.05
     অন্যান্য
    1.04
    astanza
    1.03
    𝘭
    0.96
    /−
    0.95
     melanogaster
    0.94
     ആക്രമ
    0.94
    あるいは
    0.93
    ९
    0.93
    Act Density 0.009%

    No Known Activations