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

    Neuronpedia

    INDEX
    Explanations

    nouns or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     archipelago
    0.38
     Bibliography
    0.38
     codebase
    0.38
     evolving
    0.37
     hasattr
    0.37
     apparatus
    0.36
     audience
    0.35
     mannequin
    0.35
     ہوگئی
    0.35
    GameObject
    0.35
    POSITIVE LOGITS
    Ꭺ
    0.44
    cie
    0.39
    كَ
    0.39
     gotas
    0.38
     vibes
    0.38
    𝐬
    0.37
    cards
    0.36
     nélkül
    0.36
     cues
    0.35
    ként
    0.35
    Act Density 0.395%

    No Known Activations