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

    Neuronpedia

    INDEX
    Explanations

    links, URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paramètres
    0.52
    6
    0.49
    4
    0.48
    ويلة
    0.46
     perda
    0.46
    3
    0.45
    س
    0.45
    زيد
    0.45
     finales
    0.44
    5
    0.43
    POSITIVE LOGITS
     eBay
    0.46
     Kraft
    0.44
     ETF
    0.42
     คือ
    0.42
     NGO
    0.41
    NGO
    0.41
     Miao
    0.41
    㤈
    0.41
     Wells
    0.40
     Wei
    0.40
    Act Density 0.000%

    No Known Activations