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

    Neuronpedia

    INDEX
    Explanations

    pursuant to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     więc
    0.50
    关键
    0.47
     DirectX
    0.47
    签名
    0.46
     najważ
    0.46
    ลอง
    0.43
     Krish
    0.43
     Biggest
    0.43
    魉
    0.43
     নেবার
    0.43
    POSITIVE LOGITS
     pursuant
    1.60
     Pursuant
    1.21
     conformément
    1.20
     gemäß
    0.97
     consistent
    0.91
    consistent
    0.91
     وفق
    0.86
    purs
    0.86
     zgodnie
    0.85
     accordance
    0.82
    Act Density 0.044%

    No Known Activations