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

    Neuronpedia

    INDEX
    Explanations

    what happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    2.06
    ма
    1.89
     maladie
    1.75
     eigenlijk
    1.63
    '
    1.63
    ונה
    1.54
     ngũ
    1.54
    ↵
    1.52
    atz
    1.52
     kuris
    1.52
    POSITIVE LOGITS
    此之外
    1.99
    িশালী
    1.54
    RouteChange
    1.52
    কাম
    1.51
    erweise
    1.50
     miserably
    1.50
    けど
    1.45
    ным
    1.44
    ੇ
    1.43
    办法
    1.39
    Act Density 0.151%

    No Known Activations