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

    Neuronpedia

    INDEX
    Explanations

    determinations, cautions, fluctuating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Russland
    0.45
     Experten
    0.43
     CHINA
    0.43
     ponsel
    0.43
     escolher
    0.42
    Putin
    0.42
    捅
    0.42
    সিস
    0.41
     писа
    0.41
    ,’”
    0.41
    POSITIVE LOGITS
    ائج
    0.52
    ولو
    0.50
    しみ
    0.49
     امکان
    0.48
    сцю
    0.48
    div
    0.47
    lineWidth
    0.47
    ab
    0.46
    شي
    0.46
    ंबी
    0.46
    Act Density 0.000%

    No Known Activations