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

    Neuronpedia

    INDEX
    Explanations

    R --> Descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    обс
    0.39
    }={\
    0.34
    Serializable
    0.34
    )}}{
    0.34
     vaut
    0.33
    हिंदी
    0.33
    ื่อน
    0.32
    እንደ
    0.32
    TypeOf
    0.32
    udrait
    0.32
    POSITIVE LOGITS
     उपासना
    0.40
    estabelecimento
    0.38
     छठी
    0.37
    ChangedEventArgs
    0.37
     윤
    0.36
    譙
    0.36
    PRESSED
    0.36
    enciones
    0.36
     Sue
    0.35
     establecimiento
    0.35
    Act Density 0.008%

    No Known Activations