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

    Neuronpedia

    INDEX
    Explanations

    product reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /sites
    -0.07
     natives
    -0.07
     Hund
    -0.06
    ürn
    -0.06
     deselect
    -0.06
    Gap
    -0.06
    -square
    -0.06
     cosa
    -0.06
     myfile
    -0.06
     herr
    -0.06
    POSITIVE LOGITS
     dahi
    0.07
    why
    0.06
    �s
    0.06
    ъ
    0.06
    uly
    0.06
    SECOND
    0.06
    NECT
    0.06
    кова
    0.06
    ána
    0.06
     vé
    0.06
    Act Density 0.223%

    No Known Activations