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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and structural elements in formal writing

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

    latex labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.54
     الحره
    -0.54
    expandindo
    -0.44
     disponibilités
    -0.44
    CppMethod
    -0.44
    berdayakan
    -0.43
    //-->
    -0.43
     onOptions
    -0.42
    LayoutStyle
    -0.41
     CanadaChoose
    -0.41
    POSITIVE LOGITS
    󠁢
    0.46
     AssemblyProduct
    0.42
    OWA
    0.39
    KS
    0.39
    ute
    0.39
    ftagPool
    0.39
    fro
    0.38
     Tats
    0.38
    ATN
    0.38
    KC
    0.37
    Act Density 0.007%

    No Known Activations