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

    Neuronpedia

    INDEX
    Explanations

    web parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()),
    -0.07
     yielding
    -0.07
     genomic
    -0.07
    >x
    -0.07
     הגבוה
    -0.07
    '),
    -0.07
     calcium
    -0.07
    unger
    -0.07
     kiểm
    -0.06
     Sports
    -0.06
    POSITIVE LOGITS
    AO
    0.06
     wyjaśni
    0.06
     OSD
    0.06
    罐
    0.06
    BT
    0.06
     Nothing
    0.06
    getModel
    0.06
    要做好
    0.06
    Cards
    0.06
    HAVE
    0.06
    Act Density 0.037%

    No Known Activations