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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weil
    -0.08
     beep
    -0.07
    Mario
    -0.07
    Award
    -0.06
     Institute
    -0.06
    .WebElement
    -0.06
     emperor
    -0.06
    Audit
    -0.06
    ]*)
    -0.06
    _Interface
    -0.06
    POSITIVE LOGITS
    чем
    0.06
     cryptographic
    0.06
     μπο
    0.06
    """
↵
    0.06
    ufact
    0.06
    _Request
    0.06
    ीच
    0.06
    unlikely
    0.06
     Difficulty
    0.06
    ửa
    0.06
    Act Density 0.019%

    No Known Activations