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

    Neuronpedia

    INDEX
    Explanations

    fooled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dam
    -0.07
    }/${
    -0.07
     shows
    -0.07
    增加
    -0.07
     Catal
    -0.07
    его
    -0.07
     Συ
    -0.07
    коном
    -0.07
     Shows
    -0.06
     συ
    -0.06
    POSITIVE LOGITS
    Tweet
    0.07
     ilaç
    0.06
    parcel
    0.06
     uzav
    0.06
    شن
    0.06
    registro
    0.06
    _BYTE
    0.06
     homeowners
    0.06
    CardBody
    0.06
    rot
    0.06
    Act Density 0.012%

    No Known Activations