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

    Neuronpedia

    INDEX
    Explanations

    code/citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ug
    -0.06
    ["@
    -0.06
     Dün
    -0.06
     Mehr
    -0.06
     Zd
    -0.06
    &utm
    -0.06
     Kurulu
    -0.06
    .Manager
    -0.06
    altet
    -0.06
    ihn
    -0.06
    POSITIVE LOGITS
     TensorFlow
    0.07
         ↵↵
    0.07
     undoubtedly
    0.06
    capture
    0.06
     plaintiff
    0.06
    017
    0.06
     sped
    0.06
    Doctrine
    0.06
    assignments
    0.06
    ổ
    0.06
    Act Density 0.000%

    No Known Activations