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

    Neuronpedia

    INDEX
    Explanations

    code, technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hil
    -0.07
     Afro
    -0.07
    Shows
    -0.06
     Naruto
    -0.06
    iest
    -0.06
     shall
    -0.06
    某
    -0.06
     mujer
    -0.06
     bumps
    -0.06
     milion
    -0.06
    POSITIVE LOGITS
    (routes
    0.07
     appointment
    0.07
    @SuppressWarnings
    0.06
    .persist
    0.06
    _RATE
    0.06
    /workspace
    0.06
    .jsp
    0.06
    TestCategory
    0.06
     SignUp
    0.06
    ===========↵
    0.06
    Act Density 0.000%

    No Known Activations