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

    Neuronpedia

    INDEX
    Explanations

    Asset valuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ANY
    -0.08
     ദ
    -0.08
    ANY
    -0.07
     ಕಂಪ
    -0.07
    anye
    -0.07
     comercial
    -0.07
    ASCII
    -0.07
    lowest
    -0.07
     BY
    -0.07
    -any
    -0.07
    POSITIVE LOGITS
    Women's
    0.09
     madres
    0.09
     మహిళ
    0.08
     žene
    0.08
     महिल
    0.08
     મહિલ
    0.08
     kadın
    0.08
     women's
    0.08
     Women's
    0.08
     princess
    0.08
    Act Density 0.000%

    No Known Activations