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

    Neuronpedia

    INDEX
    Explanations

    states and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Casey
    0.44
    থ
    0.42
    тся
    0.40
     স্টার
    0.38
     Casey
    0.38
     ଓ
    0.37
     CASE
    0.37
     ITEM
    0.36
     entree
    0.36
     Kne
    0.36
    POSITIVE LOGITS
     创建
    0.44
     Socialist
    0.43
    创建一个
    0.43
     フロント
    0.43
     création
    0.43
     Front
    0.42
    Front
    0.40
     असा
    0.40
    bibfnamefont
    0.39
    draft
    0.39
    Act Density 0.000%

    No Known Activations