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

    Neuronpedia

    INDEX
    Explanations

    place name origins

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Penn
    -0.08
     Una
    -0.07
    תוצאה
    -0.07
    )value
    -0.07
     Rao
    -0.07
    צת
    -0.06
    נכון
    -0.06
     nær
    -0.06
     Dame
    -0.06
     Spain
    -0.06
    POSITIVE LOGITS
    [pos
    0.08
     HOR
    0.07
     Downloads
    0.07
    (style
    0.07
    \x
    0.07
    index
    0.07
    	buff
    0.07
    [Test
    0.07
    (auto
    0.06
     crow
    0.06
    Act Density 0.019%

    No Known Activations