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

    Neuronpedia

    INDEX
    Explanations

    tell you / tell me / tell jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    2.02
     cufflinks
    1.95
     surm
    1.87
    ますが
    1.84
    岖
    1.84
    ्त
    1.80
    oons
    1.80
     digress
    1.80
    ます
    1.79
    ྒྱ
    1.74
    POSITIVE LOGITS
    ర్
    2.34
    gli
    2.05
    可以
    1.98
    Jumlah
    1.92
     Ива
    1.88
    Opens
    1.88
    Inicio
    1.78
    м
    1.78
    тые
    1.77
    Frames
    1.77
    Act Density 0.037%

    No Known Activations