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

    Neuronpedia

    INDEX
    Explanations

    fall directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Laravel
    0.57
     layanan
    0.57
     Lazada
    0.57
     TypeScript
    0.56
     `<=`
    0.56
     Xcode
    0.55
     QuantityOnHand
    0.55
     UIKit
    0.54
     Flipkart
    0.54
     ডেভেল
    0.54
    POSITIVE LOGITS
    ↵↵
    0.47
    ¬
    0.46
    chapter
    0.45
    ́
    0.45
    ъ
    0.44
     Protestant
    0.43
     pamphlet
    0.42
     Presbyterian
    0.41
    Ash
    0.41
     chast
    0.41
    Act Density 0.000%

    No Known Activations