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

    Neuronpedia

    INDEX
    Explanations

    salary ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cost
    0.44
     synd
    0.42
     "))
    0.42
     ".$
    0.41
     ")[
    0.40
     orci
    0.38
    ))
    0.38
     levels
    0.37
     promissory
    0.37
     sy
    0.37
    POSITIVE LOGITS
    щая
    0.46
    ía
    0.45
    ્ષ
    0.45
     لماذا
    0.42
    ata
    0.41
     Sixty
    0.41
    atak
    0.41
    ிற்கு
    0.40
     ৫১
    0.40
    Acer
    0.40
    Act Density 0.005%

    No Known Activations