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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons and ratios in scientific contexts

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

    mathematical expressions with brackets and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.49
    IUrlHelper
    -0.48
     تانيه
    -0.47
     EconPapers
    -0.46
    URLException
    -0.44
     beginnetje
    -0.44
    antası
    -0.43
     '\\;'
    -0.40
    Hochspringen
    -0.40
     Савезне
    -0.39
    POSITIVE LOGITS
     pleaſure
    0.47
    inistro
    0.45
    bootstrapcdn
    0.43
    ⓧ
    0.43
    kshake
    0.41
     recev
    0.39
    pragma
    0.39
     preſent
    0.38
     destra
    0.38
    issez
    0.37
    Act Density 0.553%

    No Known Activations