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

    Neuronpedia

    INDEX
    Explanations

    specific names or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    1.44
    ,
    1.43
    ،
    1.42
    ;
    1.29
    ",
    1.19
    }
    1.13
    。
    1.09
    、
    1.06
    ,\
    1.04
    ，
    1.03
    POSITIVE LOGITS
    ilene
    1.05
    ikova
    0.98
    tugraz
    0.92
     decisione
    0.91
    тари
    0.90
     assistenza
    0.88
    िक
    0.87
     Ее
    0.86
    ті
    0.84
     আসল
    0.84
    Act Density 0.092%

    No Known Activations