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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    年度
    -0.09
    .fit
    -0.08
     annual
    -0.08
     workout
    -0.08
     semester
    -0.08
     quarterly
    -0.07
    .weight
    -0.07
     nurturing
    -0.07
     jaarlijkse
    -0.07
     semesters
    -0.07
    POSITIVE LOGITS
     जमीन
    0.10
     পৃথিব
    0.10
     हवा
    0.10
     જમી
    0.09
    (frame
    0.09
     земли
    0.09
     दुनिया
    0.09
    โลก
    0.09
     مردم
    0.09
    efs
    0.08
    Act Density 0.006%

    No Known Activations