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

    Neuronpedia

    INDEX
    Explanations

    graduate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Patterns
    -0.07
     Bit
    -0.06
     politics
    -0.06
     patterns
    -0.06
    dig
    -0.06
    键
    -0.06
     theory
    -0.06
     Acid
    -0.06
     vitro
    -0.06
     scheduling
    -0.06
    POSITIVE LOGITS
     Kurulu
    0.08
    ])){↵
    0.07
     sosyal
    0.07
     �
    0.07
     Михай
    0.07
    CppObject
    0.06
     dbus
    0.06
    ्मच
    0.06
    .InnerException
    0.06
     新
    0.06
    Act Density 0.016%

    No Known Activations