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

    Neuronpedia

    INDEX
    Explanations

    target audience sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ತ್ಯ
    0.45
     kull
    0.44
     ITable
    0.43
     Exit
    0.42
    িয়োগ
    0.42
     Tool
    0.42
     Rhino
    0.42
    нтен
    0.41
     Thane
    0.41
    暨
    0.40
    POSITIVE LOGITS
    iyordu
    0.42
    I
    0.41
    al
    0.41
    ary
    0.41
    ards
    0.41
    was
    0.41
     বর্বর
    0.41
     店舗
    0.40
    ignes
    0.40
     of
    0.40
    Act Density 0.005%

    No Known Activations