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

    Neuronpedia

    INDEX
    Explanations

    prove

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dir
    -0.07
    ण
    -0.06
    ости
    -0.06
    悠
    -0.06
    itous
    -0.06
    -byte
    -0.06
    準
    -0.06
    .Monad
    -0.06
     الاج
    -0.06
     forControlEvents
    -0.06
    POSITIVE LOGITS
    >((
    0.07
     nhiên
    0.07
     станет
    0.07
    。当
    0.07
    되어
    0.06
    ":"+
    0.06
    詩
    0.06
    _modal
    0.06
     стало
    0.06
    特色
    0.06
    Act Density 0.016%

    No Known Activations