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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inaugur
    -0.08
    RELEASE
    -0.07
    正在
    -0.07
    spb
    -0.06
     фінанс
    -0.06
     сті
    -0.06
    rut
    -0.06
    ?>"><?
    -0.06
     Deb
    -0.06
     db
    -0.06
    POSITIVE LOGITS
     of
    0.08
     OF
    0.07
     chosen
    0.07
     inflamm
    0.07
    RowAt
    0.07
    MAT
    0.07
     gifted
    0.07
     �
    0.07
     AND
    0.06
    iform
    0.06
    Act Density 0.016%

    No Known Activations