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

    Neuronpedia

    INDEX
    Explanations

    listing items followed by etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    包括
    0.81
     einschließlich
    0.81
     包括
    0.81
    including
    0.80
    其中包括
    0.80
     Including
    0.79
     Whilst
    0.77
    并通过
    0.76
    と共に
    0.76
    Including
    0.75
    POSITIVE LOGITS
     et
    1.31
    Et
    1.02
     usw
    0.99
     Et
    0.96
    など
    0.91
     ect
    0.90
     ET
    0.89
     erc
    0.88
     ecc
    0.87
     वगैरह
    0.87
    Act Density 0.159%

    No Known Activations