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

    Neuronpedia

    INDEX
    Explanations

    approximate searches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boardwalk
    0.70
     embal
    0.69
     bragging
    0.67
     रिवा
    0.65
    legraph
    0.63
    ievement
    0.62
     foaming
    0.62
     putchar
    0.61
    掌
    0.61
    付属
    0.60
    POSITIVE LOGITS
     filters
    2.99
     filter
    2.97
     filtering
    2.94
     Filters
    2.84
     Filter
    2.79
     Filtering
    2.76
    Filter
    2.72
    filter
    2.70
    Filters
    2.62
     search
    2.58
    Act Density 1.309%

    No Known Activations