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

    Neuronpedia

    INDEX
    Explanations

    standardization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuzz
    -0.07
     slows
    -0.07
    нт
    -0.07
     guarantees
    -0.06
     Boulder
    -0.06
    ключ
    -0.06
     membership
    -0.06
    _unpack
    -0.06
     naked
    -0.06
     offensive
    -0.06
    POSITIVE LOGITS
    IconModule
    0.07
    larla
    0.07
    heits
    0.07
    ][/
    0.06
    _rates
    0.06
     gaining
    0.06
     आए
    0.06
    /navbar
    0.06
    ([$
    0.06
    Theo
    0.06
    Act Density 0.029%

    No Known Activations