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

    Neuronpedia

    INDEX
    Explanations

    quoted nicknames or titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     விமானங்கள்
    0.54
     groupby
    0.50
     erstellen
    0.50
     теркәлү
    0.49
     iteratively
    0.49
    PARTMENT
    0.49
     generell
    0.49
    cbind
    0.48
    oplevel
    0.48
     preprocess
    0.47
    POSITIVE LOGITS
     Captain
    0.99
     capitán
    0.89
     nicknamed
    0.88
     Mr
    0.88
     King
    0.87
    Captain
    0.85
     Monsieur
    0.85
     himself
    0.81
     king
    0.81
     Mister
    0.79
    Act Density 0.058%

    No Known Activations