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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	view
    -0.07
     Held
    -0.06
    where
    -0.06
     del
    -0.06
    _wr
    -0.06
    atures
    -0.06
    	el
    -0.06
     チ
    -0.06
    dimensions
    -0.06
    )dealloc
    -0.06
    POSITIVE LOGITS
     건강
    0.07
    neider
    0.07
    мотр
    0.07
     ("<
    0.07
    ابر
    0.06
     λόγ
    0.06
     کند
    0.06
     Southeast
    0.06
    _transfer
    0.06
     astronomers
    0.06
    Act Density 0.199%

    No Known Activations