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

    Neuronpedia

    INDEX
    Explanations

    challenges and complexities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.95
     также
    0.90
     incluindo
    0.88
     وكذلك
    0.83
     این
    0.82
     ainsi
    0.81
    ፣
    0.81
     ასევე
    0.80
     incluye
    0.80
    を使用して
    0.80
    POSITIVE LOGITS
     আদৌ
    0.82
     paltry
    0.81
     뭔
    0.76
     minuscule
    0.75
    哪怕
    0.74
     downright
    0.74
     every
    0.73
     പോലും
    0.73
     sämt
    0.72
    Wouldn
    0.71
    Act Density 0.258%

    No Known Activations