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

    Neuronpedia

    INDEX
    Explanations

    various forms of parenthesis or mathematical notation

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

    mathematical formalism features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    艋
    -0.41
    sat
    -0.39
     Incub
    -0.38
     vermelhas
    -0.38
    Sized
    -0.38
    issez
    -0.38
    =*/
    -0.37
     brancas
    -0.37
     satchel
    -0.37
     levy
    -0.36
    POSITIVE LOGITS
    awtextra
    0.53
    Parcelize
    0.44
    //
    0.43
     Gegenteil
    0.43
     sekal
    0.42
     features
    0.42
     penyebab
    0.42
    features
    0.42
    ようになって
    0.41
     oprot
    0.41
    Act Density 0.160%

    No Known Activations