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

    Neuronpedia

    INDEX
    Explanations

    in a, the, an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pInBuffer
    0.21
     น้ำ
    0.21
    '
    0.21
     或
    0.19
    ()'
    0.19
     enthält
    0.18
    '،
    0.18
    graphHead
    0.18
     iccad
    0.18
     dwRes
    0.18
    POSITIVE LOGITS
     the
    0.45
     a
    0.44
     this
    0.31
     an
    0.28
     their
    0.27
     our
    0.27
     lieu
    0.26
     your
    0.26
     terms
    0.25
     its
    0.25
    Act Density 0.475%

    No Known Activations