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

    Neuronpedia

    INDEX
    Explanations

    have their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Acid
    -0.06
    、高
    -0.06
    lica
    -0.06
    @SuppressWarnings
    -0.06
    submitted
    -0.06
     conquest
    -0.06
     Pac
    -0.06
     uploaded
    -0.06
    .Bold
    -0.06
     Thompson
    -0.06
    POSITIVE LOGITS
    ModelError
    0.07
     teď
    0.06
    .none
    0.06
    ConnectionFactory
    0.06
     Barrel
    0.06
    Ν
    0.06
     Μέ
    0.06
    نب
    0.06
     причины
    0.06
     ㅇㅇ
    0.06
    Act Density 0.153%

    No Known Activations