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

    Neuronpedia

    INDEX
    Explanations

    propagation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propagation
    -1.29
     Propagation
    -1.11
     propagating
    -0.99
     propagated
    -0.93
     propagate
    -0.91
    Propagation
    -0.88
    propagation
    -0.86
     expression
    -0.80
    propag
    -0.77
     propag
    -0.77
    POSITIVE LOGITS
     protoimpl
    0.67
    parsedMessage
    0.63
    fjspx
    0.55
    unmodifiable
    0.55
    帖最后由
    0.53
    Према
    0.50
     bump
    0.50
    istan
    0.49
     Италијани
    0.48
    HasBeenSet
    0.48
    Act Density 0.013%

    No Known Activations