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

    Neuronpedia

    INDEX
    Explanations

    Huffman coding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hemolytic
    0.55
     ARIMA
    0.52
     मणिपुर
    0.51
     магни
    0.51
     автора
    0.50
    นี้
    0.50
     αρ
    0.50
     dynamo
    0.49
     termino
    0.49
     mayors
    0.48
    POSITIVE LOGITS
    Example
    0.55
    in
    0.53
    ור
    0.51
    يد
    0.50
    ín
    0.50
     example
    0.49
     Example
    0.49
     December
    0.48
    至
    0.48
    example
    0.47
    Act Density 0.010%

    No Known Activations