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

    Neuronpedia

    INDEX
    Explanations

    remember

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اليا
    -0.06
    іїв
    -0.06
     Pek
    -0.06
     дуже
    -0.06
     औ
    -0.06
     aday
    -0.06
    ляют
    -0.06
     Mage
    -0.06
     chia
    -0.06
    explicit
    -0.06
    POSITIVE LOGITS
     remember
    0.15
    Remember
    0.13
     Remember
    0.13
    remember
    0.12
     remembering
    0.10
     remembered
    0.08
     remembers
    0.08
     recall
    0.08
     Murder
    0.07
    记
    0.07
    Act Density 0.025%

    No Known Activations