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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dyst
    -0.06
    crew
    -0.06
     Cats
    -0.06
     Went
    -0.06
     crafted
    -0.06
    �
    -0.06
     qr
    -0.06
    Our
    -0.06
    _dev
    -0.06
     bons
    -0.05
    POSITIVE LOGITS
     Aless
    0.07
    ινη
    0.07
     Εν
    0.07
     decoration
    0.07
     closing
    0.07
     Bundy
    0.06
     excell
    0.06
    .listener
    0.06
     Timeline
    0.06
     actions
    0.06
    Act Density 0.000%

    No Known Activations