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

    Neuronpedia

    INDEX
    Explanations

    features and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    网红
    0.52
    噘
    0.46
    AuthController
    0.45
    AlignedText
    0.44
    matmul
    0.42
     Firmen
    0.42
    ChatGPT
    0.41
     برج
    0.41
     Beyoncé
    0.41
    фессиона
    0.41
    POSITIVE LOGITS
     attribute
    0.84
     Attribute
    0.75
     attributes
    0.68
    Attribute
    0.66
     discretization
    0.64
    attribute
    0.64
     datasets
    0.64
     pruning
    0.64
     Attributes
    0.63
     classifiers
    0.63
    Act Density 0.048%

    No Known Activations