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

    Neuronpedia

    INDEX
    Explanations

    describe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     موس
    -0.07
    _sym
    -0.07
     옥
    -0.07
    ACL
    -0.06
     AX
    -0.06
    Tem
    -0.06
     köln
    -0.06
     malicious
    -0.06
    BOSE
    -0.06
     skins
    -0.06
    POSITIVE LOGITS
     IBOutlet
    0.07
    леж
    0.07
    arked
    0.06
    říklad
    0.06
    発
    0.06
    اپیم
    0.06
    圭圭
    0.06
    cation
    0.06
    XmlAttribute
    0.06
     filmed
    0.06
    Act Density 0.037%

    No Known Activations