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

    Neuronpedia

    INDEX
    Explanations

    phenomena and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    suite
    0.69
    नावली
    0.64
    豊富
    0.63
     Lynn
    0.63
    graphql
    0.62
    灵活
    0.61
    世界的
    0.61
    PackageManager
    0.61
     કંઈ
    0.61
     எதிர்க
    0.60
    POSITIVE LOGITS
     effect
    2.04
    现象
    1.94
    現象
    1.88
     phenomenon
    1.87
     Effect
    1.74
    效应
    1.73
     effects
    1.66
     phénomène
    1.66
     phenomena
    1.65
     coefficient
    1.56
    Act Density 0.450%

    No Known Activations