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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.07
    县
    -0.07
    The
    -0.07
     раньше
    -0.06
     The
    -0.06
     fashionable
    -0.06
    Increased
    -0.06
     شرقی
    -0.06
     проти
    -0.06
    変更
    -0.06
    POSITIVE LOGITS
    \uD
    0.07
     unearth
    0.07
    IRMWARE
    0.07
     Vaccine
    0.07
    atches
    0.06
     Palm
    0.06
     unfamiliar
    0.06
    azon
    0.06
    icum
    0.06
     Morrow
    0.06
    Act Density 0.090%

    No Known Activations