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

    Neuronpedia

    INDEX
    Explanations

    diagram or figure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quería
    0.46
     خدمات
    0.45
     murderous
    0.45
    ᚨ
    0.43
     homophobic
    0.42
     prostit
    0.42
     evoc
    0.41
     auth
    0.41
     discursive
    0.40
    денциа
    0.40
    POSITIVE LOGITS
    图中
    0.66
    如图
    0.64
     shown
    0.52
    图
    0.52
    所示
    0.49
     depicted
    0.48
    pictured
    0.47
    如下图
    0.46
     изобра
    0.46
    Figure
    0.45
    Act Density 0.040%

    No Known Activations