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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.46
    นต์
    0.45
    น
    0.45
    نا
    0.43
     ア
    0.43
    ア
    0.43
     när
    0.43
    ə
    0.42
     sekali
    0.42
    餸
    0.42
    POSITIVE LOGITS
    0.50
    :
    0.44
    ação
    0.43
     cobbled
    0.42
    이며
    0.41
     omitted
    0.39
     등의
    0.38
    _
    0.37
     chiral
    0.37
    이라고
    0.36
    Act Density 0.094%

    No Known Activations