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

    Neuronpedia

    INDEX
    Explanations

    logic/sufficiency problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     |_
    -0.08
    missions
    -0.08
     psychologist
    -0.08
     refs
    -0.08
    मिक
    -0.07
     priro
    -0.07
     വരുന്ന
    -0.07
    برنامج
    -0.07
     письмо
    -0.07
     الطبي
    -0.07
    POSITIVE LOGITS
     and
    0.09
     Jensen
    0.08
    977
    0.07
     erfüllt
    0.07
     married
    0.07
    /
    0.07
     incline
    0.07
     farmland
    0.07
    :
    0.07
     Married
    0.07
    Act Density 0.025%

    No Known Activations