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

    Neuronpedia

    INDEX
    Explanations

    math logic problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ప్రక
    -0.08
     voluntary
    -0.07
     Difference
    -0.07
    Difference
    -0.07
     certe
    -0.07
     gelir
    -0.07
     Amy
    -0.07
     τις
    -0.07
     FOB
    -0.07
     التص
    -0.07
    POSITIVE LOGITS
     lace
    0.09
     несколь
    0.09
     nú
    0.08
     Spar
    0.08
     spar
    0.08
    ijske
    0.08
     accueillir
    0.07
    /About
    0.07
     Lis
    0.07
     accueille
    0.07
    Act Density 0.026%

    No Known Activations