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

    Neuronpedia

    INDEX
    Explanations

    plugins, loaders, and adapters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⚌
    0.44
    ⿸
    0.41
     फी
    0.40
    нома
    0.40
    <0xD2>
    0.40
     ಮಧ್ಯ
    0.40
    currentGame
    0.39
    筤
    0.39
    боли
    0.38
     Alcoholic
    0.38
    POSITIVE LOGITS
    babel
    0.66
     plugin
    0.65
    jsx
    0.63
    插件
    0.61
    plugin
    0.61
     babel
    0.60
     plugins
    0.59
    preset
    0.58
    syntax
    0.58
     transform
    0.58
    Act Density 0.006%

    No Known Activations