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

    Neuronpedia

    INDEX
    Explanations

    philosophical subjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suatu
    0.50
    出典
    0.45
     uzman
    0.45
    ńst
    0.43
     powied
    0.43
    𝒏
    0.42
     eponym
    0.42
    ர்ஸ்
    0.41
    otrexate
    0.41
    သွ
    0.41
    POSITIVE LOGITS
    ipt
    0.52
    ipe
    0.46
     artists
    0.45
    Facade
    0.44
     पटाखे
    0.44
    for
    0.43
    odd
    0.43
     سوال
    0.42
     event
    0.42
    oi
    0.41
    Act Density 0.005%

    No Known Activations