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

    Neuronpedia

    INDEX
    Explanations

    poisoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >b
    -0.07
     '.')
    -0.07
    дет
    -0.07
    getSize
    -0.07
    ारक
    -0.06
    subs
    -0.06
     pins
    -0.06
    ],[-
    -0.06
    "'↵
    -0.06
    fulWidget
    -0.06
    POSITIVE LOGITS
     poisoning
    0.10
     сол
    0.07
    iversal
    0.06
    говор
    0.06
    ówn
    0.06
    isbury
    0.06
    صح
    0.06
    chemist
    0.06
    ulong
    0.06
     chóng
    0.06
    Act Density 0.003%

    No Known Activations