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

    Neuronpedia

    INDEX
    Explanations

    code separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    221
    -0.06
     chants
    -0.06
    _structure
    -0.06
    Err
    -0.06
    ştır
    -0.06
    isté
    -0.06
    áf
    -0.06
     Award
    -0.06
    _strategy
    -0.06
    uml
    -0.05
    POSITIVE LOGITS
    crawler
    0.07
    ево
    0.07
    /sbin
    0.06
     Мі
    0.06
     ミ
    0.06
     hopefully
    0.06
    زل
    0.06
    裂
    0.06
    (cells
    0.06
    PFN
    0.06
    Act Density 0.007%

    No Known Activations