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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theft
    -0.07
    hotmail
    -0.07
     Ulus
    -0.06
    Jul
    -0.06
     kvinn
    -0.06
     seminar
    -0.06
    ДК
    -0.06
     Нат
    -0.06
    ubuntu
    -0.06
    Marco
    -0.06
    POSITIVE LOGITS
     stabilize
    0.06
    就在
    0.06
    Sdk
    0.06
    ักเร
    0.06
     AN
    0.06
     등록
    0.06
     Started
    0.06
     =================================================================
    0.06
    _SKIP
    0.06
    ัวเอง
    0.06
    Act Density 0.017%

    No Known Activations