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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    iação
    -0.08
     программа
    -0.08
    wahl
    -0.08
     réflex
    -0.08
    werkingen
    -0.08
    اريع
    -0.08
    .heroku
    -0.08
     ведь
    -0.07
     Complimentary
    -0.07
    POSITIVE LOGITS
     perpetr
    0.10
    recent
    0.09
     incidents
    0.09
     victims
    0.09
     perpetrators
    0.09
    Crime
    0.09
     alleging
    0.09
     xảy
    0.09
    犯罪
    0.09
     reciente
    0.09
    Act Density 0.091%
    No Known Activations