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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

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

    nearest or smallest comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.47
    الحياه
    -0.46
    ंदीखरीदारी
    -0.43
    extAlignment
    -0.43
     gwaran
    -0.42
    utilisons
    -0.42
    IUrlHelper
    -0.41
     betweenstory
    -0.41
    ACHUSET
    -0.41
    磕
    -0.41
    POSITIVE LOGITS
    jspx
    0.47
     thermometer
    0.39
     برف
    0.39
     MutableLiveData
    0.39
     виправивши
    0.37
     leash
    0.37
     hole
    0.36
     surla
    0.35
     libra
    0.35
     препратки
    0.35
    Act Density 1.163%

    No Known Activations