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

    Neuronpedia

    INDEX
    Explanations

    任

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    includes
    -0.07
     Already
    -0.07
     Initially
    -0.07
     anticipating
    -0.06
    IVED
    -0.06
     constitute
    -0.06
    لفة
    -0.06
    PB
    -0.06
    arefa
    -0.06
     Furthermore
    -0.06
    POSITIVE LOGITS
    ()<<
    0.07
    (utils
    0.07
    �
    0.06
    "](
    0.06
     resetting
    0.06
    .bs
    0.06
     Doll
    0.06
     RIGHTS
    0.06
     ENTER
    0.06
     spelling
    0.06
    Act Density 0.000%

    No Known Activations