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

    Neuronpedia

    INDEX
    Explanations

    French administrative divisions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tur
    -0.07
     dumped
    -0.07
     serait
    -0.07
     enumerable
    -0.07
    全年
    -0.07
    ירוש
    -0.07
    MJ
    -0.07
    業務
    -0.07
    永久
    -0.07
     Pir
    -0.07
    POSITIVE LOGITS
    Ⱀ
    0.07
    ORD
    0.07
    现实
    0.06
    BLEM
    0.06
    妙
    0.06
     Sob
    0.06
    olv
    0.06
    obi
    0.06
     cof
    0.06
    咚
    0.06
    Act Density 0.023%

    No Known Activations