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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disclosure and personal expression

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

    action verbs with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataTo
    -0.37
     }}"></
    -0.36
    zama
    -0.36
    таратура
    -0.34
    enschappelijke
    -0.32
    poved
    -0.31
    dcterms
    -0.31
    зво
    -0.30
    зулта
    -0.30
    StringTo
    -0.29
    POSITIVE LOGITS
     EconPapers
    0.74
     pinulongan
    0.69
    AndEndTag
    0.65
     ujednoznacz
    0.64
     للاسماء
    0.57
    0.56
     '\\;'
    0.56
    HostException
    0.55
     beginnetje
    0.55
     AssemblyCompany
    0.54
    Act Density 0.047%

    No Known Activations