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

    Neuronpedia

    INDEX
    Explanations

    code validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Settings
    -0.07
    doctrine
    -0.06
    RE
    -0.06
     Warn
    -0.06
    �
    -0.06
    ALL
    -0.06
    DATED
    -0.06
    Strong
    -0.06
    Gal
    -0.06
     le
    -0.06
    POSITIVE LOGITS
     USART
    0.07
     yorum
    0.06
     yön
    0.06
     edil
    0.06
    大學
    0.06
    otlin
    0.06
     [&
    0.06
     doit
    0.06
     bunk
    0.06
     subsection
    0.06
    Act Density 0.151%

    No Known Activations