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

    Neuronpedia

    INDEX
    Explanations

    Abu Ghraib, Guantanamo prisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Prime
    -0.07
    eting
    -0.06
    جب
    -0.06
    вания
    -0.06
     Times
    -0.06
     вул
    -0.06
    imes
    -0.06
     tưởng
    -0.06
    aus
    -0.06
     weekends
    -0.06
    POSITIVE LOGITS
     Need
    0.07
    (any
    0.07
     فض
    0.07
    ８
    0.07
     componentWill
    0.07
     Foley
    0.07
     Supports
    0.06
    automatic
    0.06
     Everest
    0.06
    Lens
    0.06
    Act Density 0.017%

    No Known Activations