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

    Neuronpedia

    INDEX
    Explanations

    links to .org websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cardiac
    0.23
     ```
    0.23
    ımız
    0.22
    0.22
     Durchführung
    0.22
     Cons
    0.22
    無論
    0.21
     Poetry
    0.21
     यदि
    0.20
     अपेक्षा
    0.20
    POSITIVE LOGITS
    vendo
    0.23
     voltou
    0.23
    サングラス
    0.22
     võ
    0.22
     пе
    0.22
     legais
    0.22
     curbs
    0.21
     giới
    0.21
    ワールド
    0.21
     personalizar
    0.21
    Act Density 0.002%

    No Known Activations