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

    Neuronpedia

    INDEX
    Explanations

    remembering instructions or warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     repulsive
    0.52
     sunflower
    0.51
     fibroblast
    0.49
     decolor
    0.48
    '
    0.48
     furtherance
    0.48
     sulfide
    0.47
     ним
    0.47
     অনে
    0.47
     inconsist
    0.46
    POSITIVE LOGITS
    Remember
    0.78
    remember
    0.77
     remember
    0.76
     Remember
    0.75
     помнить
    0.63
    า
    0.62
    记得
    0.61
     remembers
    0.59
     recuerda
    0.59
     pamię
    0.59
    Act Density 0.038%

    No Known Activations