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

    Neuronpedia

    INDEX
    Explanations

    pronouns and "is"/"are"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     createContext
    -0.56
     (“
    -0.56
     („
    -0.52
     estoppel
    -0.48
     pleaſure
    -0.47
    ﴾
    -0.47
     hendes
    -0.47
     («
    -0.47
     ("
    -0.47
    raits
    -0.45
    POSITIVE LOGITS
    DoubleQuotes
    0.75
    ValueStyle
    0.68
    SequentialGroup
    0.63
    InputBorder
    0.62
     isEqualToString
    0.60
     disambiguazione
    0.56
    makeConstraints
    0.56
    EndInit
    0.55
    NOPQRST
    0.55
    Chooser
    0.54
    Act Density 0.003%

    No Known Activations