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

    Neuronpedia

    INDEX
    Explanations

    As

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aku
    -0.07
    thead
    -0.07
     vyt
    -0.06
    ést
    -0.06
    fik
    -0.06
    (dr
    -0.06
    _MAGIC
    -0.06
    핀
    -0.06
    ‌پدی
    -0.06
     я
    -0.06
    POSITIVE LOGITS
     As
    0.07
    “As
    0.07
    As
    0.06
    "As
    0.06
     bü
    0.06
    .managed
    0.06
    UGHT
    0.06
    종
    0.06
    gens
    0.06
    Filled
    0.06
    Act Density 0.037%

    No Known Activations