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

    Neuronpedia

    INDEX
    Explanations

    attention mechanisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۴۰
    -0.07
    .Sqrt
    -0.07
    ۳۵
    -0.07
     prostitut
    -0.06
    린이
    -0.06
    !*\↵
    -0.06
    σπ
    -0.06
     glor
    -0.06
     filt
    -0.06
    .filtered
    -0.06
    POSITIVE LOGITS
     weren
    0.07
     signalling
    0.07
     Honduras
    0.07
     notions
    0.06
    Research
    0.06
     defiant
    0.06
     assume
    0.06
     directed
    0.06
     lasted
    0.06
     façon
    0.06
    Act Density 0.010%

    No Known Activations