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

    Neuronpedia

    INDEX
    Explanations

    common short words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Running
    -0.06
    .recipe
    -0.06
    ophage
    -0.06
    áo
    -0.06
    .TestCase
    -0.06
    .variant
    -0.06
     thơm
    -0.06
     จาก
    -0.06
    .car
    -0.06
    職
    -0.06
    POSITIVE LOGITS
     attorney
    0.07
    _rating
    0.06
     Futures
    0.06
     portfolio
    0.06
    레이
    0.06
    reg
    0.06
    _DEFINITION
    0.06
     hyp
    0.06
    egree
    0.06
    verter
    0.06
    Act Density 0.114%

    No Known Activations