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

    Neuronpedia

    INDEX
    Explanations

    terms related to the introduction of new language or slang

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

    coined the term, slang, or vernacular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.45
     Duty
    -0.42
                                   
    -0.42
     Erm
    -0.40
     duty
    -0.40
                                 
    -0.40
     Speck
    -0.40
     allAfrica
    -0.39
    ESTRO
    -0.38
    subsubsection
    -0.38
    POSITIVE LOGITS
     coined
    1.26
     slang
    1.05
     colloquial
    0.83
     invented
    0.69
     coinage
    0.66
     jargon
    0.62
     originated
    0.61
    цездатний
    0.59
    تقاوى
    0.59
    manteau
    0.58
    Act Density 0.028%

    No Known Activations