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

    Neuronpedia

    INDEX
    Explanations

    fix adjust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <object
    -0.07
    WRAPPER
    -0.07
    .Loader
    -0.07
    聘
    -0.06
    過
    -0.06
     trailers
    -0.06
    Pa
    -0.06
    Texas
    -0.06
    田
    -0.06
    _inv
    -0.06
    POSITIVE LOGITS
     Hep
    0.07
     lạ
    0.07
     Entrepreneur
    0.07
     exercising
    0.06
    ění
    0.06
    icros
    0.06
     renown
    0.06
    ème
    0.06
     Mét
    0.06
    owns
    0.06
    Act Density 0.048%

    No Known Activations