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

    Neuronpedia

    INDEX
    Explanations

    sequential punctuation marks and structure in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.65
     مرئيه
    -0.56
    WhereInput
    -0.56
    tonode
    -0.52
     pinulongan
    -0.51
    GEBURTSDATUM
    -0.47
    DeleteBehavior
    -0.45
    ValueGenerated
    -0.43
    StackNavigator
    -0.42
    MLLoader
    -0.41
    POSITIVE LOGITS
    Abitanti
    0.47
    ypeł
    0.43
    EndProject
    0.37
     itſelf
    0.37
    literals
    0.35
    contentLoaded
    0.35
     useAppContext
    0.34
    brium
    0.34
     operazioni
    0.33
     tasche
    0.33
    Act Density 0.008%

    No Known Activations