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

    Neuronpedia

    INDEX
    Explanations

    computers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     app
    -0.07
    átku
    -0.07
     focusing
    -0.06
     cipher
    -0.06
     krás
    -0.06
     sectors
    -0.06
    .rd
    -0.06
    _literals
    -0.06
    task
    -0.06
    ز
    -0.06
    POSITIVE LOGITS
    nosti
    0.07
     테
    0.07
    证明
    0.07
     коли
    0.06
     바람
    0.06
     मल
    0.06
    (","
    0.06
    nost
    0.06
     "),↵
    0.06
     Advis
    0.06
    Act Density 0.129%

    No Known Activations