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

    Neuronpedia

    INDEX
    Explanations

    foreign prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weld
    -0.07
    obic
    -0.06
    -tw
    -0.06
     advertis
    -0.06
     nour
    -0.06
     chloride
    -0.06
     tespit
    -0.06
     specializes
    -0.06
    [U
    -0.06
    ٥
    -0.06
    POSITIVE LOGITS
     BUFF
    0.07
    �
    0.07
     письмен
    0.07
    ิถ
    0.06
     가족
    0.06
    .qty
    0.06
    /vector
    0.06
    	fflush
    0.06
    .Refresh
    0.06
    _SORT
    0.06
    Act Density 0.053%

    No Known Activations