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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     semiconductor
    -0.07
    (inflater
    -0.07
     مسلمان
    -0.06
    .viewmodel
    -0.06
    Lambda
    -0.06
     Bec
    -0.06
    /kubernetes
    -0.06
    .teacher
    -0.06
    .AWS
    -0.06
     lateinit
    -0.06
    POSITIVE LOGITS
    (resultado
    0.07
    斗
    0.07
     Presented
    0.06
    (clean
    0.06
    .double
    0.06
     rifles
    0.06
    truth
    0.06
    walls
    0.06
     universally
    0.06
    /bash
    0.06
    Act Density 0.001%

    No Known Activations