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

    Neuronpedia

    INDEX
    Explanations

    logger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arger
    -0.07
    тивного
    -0.06
     mainstream
    -0.06
    RegularExpression
    -0.06
    inary
    -0.06
     عباس
    -0.06
    CanBe
    -0.06
    بي
    -0.06
     Equality
    -0.06
     freder
    -0.06
    POSITIVE LOGITS
     Blogger
    0.09
     blogger
    0.07
    ?#
    0.06
     ig
    0.06
    _property
    0.06
    	sh
    0.06
     toddler
    0.06
    ık
    0.06
    ευ
    0.05
    TestCategory
    0.05
    Act Density 0.001%

    No Known Activations