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

    Neuronpedia

    INDEX
    Explanations

    code comments and copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rote
    -0.07
    .Bool
    -0.07
    .Column
    -0.07
     Ames
    -0.07
     Hib
    -0.07
    �
    -0.07
    ˬ
    -0.07
    独有的
    -0.06
    ATURE
    -0.06
    ]>↵
    -0.06
    POSITIVE LOGITS
     Pact
    0.08
    texts
    0.07
    hell
    0.07
    -sectional
    0.07
    ятия
    0.07
    عار
    0.07
    大海
    0.07
    代谢
    0.07
    لح
    0.07
    ẽ
    0.06
    Act Density 0.036%

    No Known Activations