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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    词
    -0.07
     Curriculum
    -0.07
    isRequired
    -0.06
     Av
    -0.06
     Williamson
    -0.06
    �
    -0.06
     km
    -0.06
     Brilliant
    -0.06
     Barth
    -0.06
     coeff
    -0.06
    POSITIVE LOGITS
    byname
    0.07
    _beh
    0.06
    .assertIsNot
    0.06
    ीग
    0.06
    -pt
    0.06
    TokenType
    0.06
    ollar
    0.06
    empor
    0.06
     thy
    0.06
    .FALSE
    0.06
    Act Density 0.000%

    No Known Activations