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

    Neuronpedia

    INDEX
    Explanations

    correctness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GPUs
    -0.07
     homer
    -0.07
    .disk
    -0.06
     مشکلات
    -0.06
     "()
    -0.06
     sprinkle
    -0.06
     Tac
    -0.06
    .Ultra
    -0.06
    ันย
    -0.06
    _drag
    -0.06
    POSITIVE LOGITS
    іч
    0.07
     successful
    0.07
     daughter
    0.06
    available
    0.06
     Checkout
    0.06
     therapist
    0.06
     estimating
    0.06
     clase
    0.06
     Why
    0.06
    hy
    0.06
    Act Density 0.061%

    No Known Activations