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

    Neuronpedia

    INDEX
    Explanations

    new car models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     floods
    -0.07
     SIL
    -0.07
    oes
    -0.07
     Coral
    -0.07
     mondo
    -0.06
     Jud
    -0.06
    (Char
    -0.06
     ETH
    -0.06
     Bread
    -0.06
     Your
    -0.06
    POSITIVE LOGITS
    ением
    0.07
    _fun
    0.06
     xyz
    0.06
     TestCase
    0.06
    [type
    0.06
     disjoint
    0.06
    .assertIn
    0.06
    uitka
    0.06
     tabindex
    0.06
     pytest
    0.06
    Act Density 0.028%

    No Known Activations