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

    Neuronpedia

    INDEX
    Explanations

    explanation of steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    피
    0.40
     головы
    0.38
     желу
    0.37
    図
    0.37
    Diagram
    0.37
    Д
    0.37
     мая
    0.36
     ওয়া
    0.36
    メン
    0.36
     Гла
    0.36
    POSITIVE LOGITS
     Chim
    0.40
    visory
    0.40
    '।
    0.39
     Chimie
    0.39
    chon
    0.39
     mandar
    0.38
    standards
    0.38
    ్రె
    0.38
    imab
    0.38
    ','')
    0.38
    Act Density 0.001%

    No Known Activations