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

    Neuronpedia

    INDEX
    Explanations

    full equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نصی
    0.79
     rekomend
    0.77
    selectTable
    0.77
     etsy
    0.77
     स्त
    0.76
    Trivia
    0.75
     superlative
    0.75
     hummus
    0.72
     neckline
    0.72
    searchValue
    0.71
    POSITIVE LOGITS
     simulation
    2.76
     simulations
    2.64
     Simulation
    2.45
    Simulation
    2.40
     modeling
    2.34
     Simulations
    2.32
    simulation
    2.26
     simulating
    2.25
     simulate
    2.24
     modelling
    2.24
    Act Density 0.557%

    No Known Activations