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

    Neuronpedia

    INDEX
    Explanations

    .dtd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çek
    -0.07
    yro
    -0.07
     شي
    -0.07
     cav
    -0.06
     שהיו
    -0.06
     cleanup
    -0.06
     dildo
    -0.06
     superheroes
    -0.06
    _ext
    -0.06
    有一些
    -0.06
    POSITIVE LOGITS
    =E
    0.08
    inqu
    0.07
    =self
    0.07
    ernal
    0.06
    0.06
    =dict
    0.06
    	read
    0.06
    ➠
    0.06
    beck
    0.06
     [↵↵
    0.06
    Act Density 0.000%

    No Known Activations