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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical symbols or expressions

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

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.69
    MLLoader
    -0.61
    ьаж
    -0.60
     resourceCulture
    -0.60
     doInBackground
    -0.59
    WriteTagHelper
    -0.58
    ViewFeatures
    -0.55
    PyExc
    -0.55
     informée
    -0.55
    ंदीखरीदारी
    -0.52
    POSITIVE LOGITS
     etc
    0.49
    例の
    0.44
     Here
    0.42
    break
    0.41
    etc
    0.41
    Expected
    0.38
     detail
    0.37
     Expected
    0.37
     promise
    0.37
     e
    0.37
    Act Density 0.061%

    No Known Activations