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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     각각
    -0.08
    (dot
    -0.08
     mě
    -0.08
    PERTIES
    -0.08
    นาด
    -0.07
     ermöglicht
    -0.07
    리
    -0.07
     추
    -0.07
     이러한
    -0.07
     sehingga
    -0.07
    POSITIVE LOGITS
    Generally
    0.08
     vigilant
    0.08
     Generally
    0.08
     China's
    0.08
     Vigil
    0.08
     éviter
    0.08
    ASI
    0.08
     unintended
    0.07
     omissions
    0.07
     religión
    0.07
    Act Density 0.017%

    No Known Activations