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

    Neuronpedia

    INDEX
    Explanations

    unsafe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پوش
    -0.08
     diamond
    -0.07
    ۲۴
    -0.07
     cluster
    -0.07
    400
    -0.07
    Michael
    -0.07
     голод
    -0.07
     groups
    -0.07
    GMT
    -0.06
    .Total
    -0.06
    POSITIVE LOGITS
     unsafe
    0.07
    unsafe
    0.07
     vivastreet
    0.06
     счита
    0.06
    ibase
    0.06
    .IM
    0.06
    emade
    0.06
     العام
    0.06
     Sunni
    0.06
     valuation
    0.06
    Act Density 0.002%

    No Known Activations