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

    Neuronpedia

    INDEX
    Explanations

    elements and food items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gerçekleş
    0.36
    讵
    0.35
     kişinin
    0.33
     süreç
    0.33
     άνθρω
    0.32
     юриди
    0.32
     ανθρώ
    0.32
    骠
    0.31
     cüm
    0.31
    vrir
    0.31
    POSITIVE LOGITS
    -
    0.42
     dioxide
    0.41
    aceous
    0.39
    centric
    0.37
     satin
    0.37
     seedlings
    0.36
     flour
    0.36
     atoms
    0.35
    ī
    0.35
    тами
    0.35
    Act Density 0.303%

    No Known Activations