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

    Neuronpedia

    INDEX
    Explanations

    plugins and extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‘
    0.44
    ᆭ
    0.42
     puncak
    0.41
    Ͻ
    0.41
    ന്ത
    0.40
    Kinder
    0.40
    ableConcept
    0.38
    ftÂ
    0.38
     unabhängig
    0.38
    hauses
    0.38
    POSITIVE LOGITS
     plugin
    1.07
    插件
    1.06
     plugins
    1.04
    plugin
    0.94
    Plugin
    0.88
     Plugin
    0.88
     Plugins
    0.84
    plugins
    0.82
    プラグ
    0.70
     extensions
    0.69
    Act Density 0.024%

    No Known Activations