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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence structures

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

    explaining information details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.71
    ImageContext
    -0.68
     الحره
    -0.64
     '\\;'
    -0.64
    httphttps
    -0.62
    styleType
    -0.61
     للاسماء
    -0.60
    tagHelperRunner
    -0.58
     kasarigan
    -0.58
    Datuak
    -0.57
    POSITIVE LOGITS
     describe
    0.42
    describe
    0.41
     details
    0.40
     Lehr
    0.40
     how
    0.40
     tale
    0.40
    についても
    0.40
    ungsver
    0.38
    how
    0.36
     explain
    0.36
    Act Density 0.162%

    No Known Activations