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

    Neuronpedia

    INDEX
    Explanations

    terms and references related to news sources and specific publications

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

    Huffington Post, HL quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     móc
    -0.37
    ╣
    -0.34
     colorful
    -0.34
     LE
    -0.34
     Toc
    -0.34
     Plan
    -0.33
     Wing
    -0.33
    عات
    -0.33
    thâu
    -0.33
    ώς
    -0.32
    POSITIVE LOGITS
     GenerationType
    0.56
    GOTREF
    0.54
     &___
    0.52
     يتيمه
    0.51
     Betracht
    0.50
    parsedMessage
    0.50
    tagHelperRunner
    0.49
     ***!
    0.49
    intios
    0.48
    Vaata
    0.47
    Act Density 0.009%

    No Known Activations