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

    Neuronpedia

    INDEX
    Explanations

    instructions or prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notions
    0.47
     sembl
    0.45
     nods
    0.44
     durchaus
    0.44
     nejsou
    0.43
    餑
    0.43
     termes
    0.42
     crystallinity
    0.42
     deviennent
    0.41
     nulle
    0.41
    POSITIVE LOGITS
     Seorang
    0.55
     seorang
    0.52
     Farmer
    0.52
    已知
    0.50
     Suppose
    0.50
    Imagine
    0.49
    在一个
    0.48
     How
    0.48
    为一个
    0.47
    一位
    0.46
    Act Density 0.044%

    No Known Activations