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

    Neuronpedia

    INDEX
    Explanations

    debate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     religions
    -0.07
     하지
    -0.07
    ewolf
    -0.06
     intention
    -0.06
    стру
    -0.06
    दम
    -0.06
     Blanc
    -0.06
    .goto
    -0.06
     маг
    -0.06
     idle
    -0.06
    POSITIVE LOGITS
    Csv
    0.07
    .twig
    0.06
     Outstanding
    0.06
    Leaks
    0.06
     Reconstruction
    0.06
    <Model
    0.06
    shots
    0.06
    utedString
    0.06
    úp
    0.06
     सभ
    0.06
    Act Density 0.009%

    No Known Activations