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

    Neuronpedia

    INDEX
    Explanations

    phrases related to syntactic structure and grammatical rules

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

    word or punctuation followed by prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.70
     désolés
    -0.61
     propOrder
    -0.59
    ToBounds
    -0.56
     يتيمه
    -0.54
     ModelRenderer
    -0.54
    FirstResponder
    -0.54
     Chwiliwch
    -0.53
    DECREF
    -0.52
     autorytatywna
    -0.52
    POSITIVE LOGITS
     prefixes
    0.43
     prefix
    0.37
     suffix
    0.32
    Etimología
    0.31
     Prefix
    0.31
    FFIX
    0.30
     suffixes
    0.30
     gesteld
    0.29
     Bearbeitung
    0.28
     combineReducers
    0.28
    Act Density 0.191%

    No Known Activations