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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zaw
    -0.06
     hook
    -0.06
    Aff
    -0.06
    имер
    -0.06
     nulla
    -0.06
     unprotected
    -0.06
     knowingly
    -0.06
     궁금
    -0.05
    PYTHON
    -0.05
    úmero
    -0.05
    POSITIVE LOGITS
    ーション
    0.07
     конферен
    0.07
    uche
    0.07
     Logan
    0.07
     Thankfully
    0.07
    595
    0.07
     Should
    0.06
    543
    0.06
    _ASSERT
    0.06
    navigate
    0.06
    Act Density 0.681%

    No Known Activations