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

    Neuronpedia

    INDEX
    Explanations

    linguistic terms related to grammatical categories and modifiers

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

    grammatical and semantic categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.70
     للاسماء
    -0.65
     kaynağından
    -0.58
    Хьажоргаш
    -0.51
    UserScript
    -0.50
     defaultstate
    -0.49
    FieldBuilder
    -0.49
    ViewFeatures
    -0.48
    StringCopy
    -0.47
    FieldNumber
    -0.47
    POSITIVE LOGITS
     ordin
    0.42
     progre
    0.35
    怎
    0.35
    IonicModule
    0.33
    oteo
    0.33
     Ordin
    0.33
     laki
    0.33
    ính
    0.32
     priv
    0.32
    ポーター
    0.32
    Act Density 0.170%

    No Known Activations