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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Combined
    -0.07
     워
    -0.07
     ø
    -0.07
     chests
    -0.07
     Concrete
    -0.07
     refusing
    -0.06
     festivals
    -0.06
     Dock
    -0.06
     chung
    -0.06
    GROUP
    -0.06
    POSITIVE LOGITS
     responsable
    0.07
     пост
    0.07
    ／/
    0.06
    conc
    0.06
    ीं।
    0.06
    diag
    0.06
    _storage
    0.06
     utan
    0.06
     nost
    0.06
     благодаря
    0.06
    Act Density 0.000%

    No Known Activations