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

    Neuronpedia

    INDEX
    Explanations

    concepts with subsequent qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -1.13
    -1.09
    regarding
    -1.06
    ㈯
    -1.03
    Rwanda
    -1.00
     garan
    -1.00
    いよいよ
    -1.00
    絝
    -0.98
    recently
    -0.98
     véhic
    -0.97
    POSITIVE LOGITS
     if
    1.20
     of
    1.17
     in
    1.16
     that
    1.16
     on
    1.14
     (
    1.13
     at
    1.05
    8
    1.01
     within
    1.01
     this
    1.00
    Act Density 0.030%

    No Known Activations