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

    Neuronpedia

    INDEX
    Explanations

    write a program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    1.30
    ك
    1.08
    بة
    1.07
     be
    1.03
    า
    1.03
    1.01
    માં
    0.98
    to
    0.93
    س
    0.91
    的
    0.88
    POSITIVE LOGITS
    お店
    1.04
    혔
    1.02
    ０
    0.99
    った
    0.95
     Само
    0.93
    お客様
    0.88
     indiquer
    0.87
     programmi
    0.86
     attendants
    0.86
     hatched
    0.86
    Act Density 0.235%

    No Known Activations