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

    Neuronpedia

    INDEX
    Explanations

    breakdown of why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skepticism
    0.47
     compagnies
    0.43
     ಅಭಿ
    0.42
     versionCode
    0.42
     promoters
    0.41
    parachute
    0.41
     parabolic
    0.40
     условии
    0.40
    committees
    0.40
     amac
    0.39
    POSITIVE LOGITS
    Baş
    0.52
    Actions
    0.46
     Actions
    0.46
     Removed
    0.46
     Action
    0.45
    Action
    0.45
     Какие
    0.45
    Removed
    0.44
    服务
    0.43
     मंगलवार
    0.42
    Act Density 0.091%

    No Known Activations