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

    Neuronpedia

    INDEX
    Explanations

    references to academic workshops and conferences

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

    academic events like workshops or symposiums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.41
     säga
    -0.38
     resourceCulture
    -0.38
     CIP
    -0.38
     habet
    -0.37
     raggi
    -0.36
     hacerte
    -0.36
    Lähteet
    -0.36
     igualmente
    -0.36
    ilber
    -0.36
    POSITIVE LOGITS
    TagMode
    0.59
    httphttps
    0.52
    tagHelperRunner
    0.49
     EconPapers
    0.47
     externi
    0.45
     betweenstory
    0.45
    expert
    0.45
    ỏi
    0.42
    optionalTypeArgs
    0.42
     BorderRadius
    0.42
    Act Density 0.035%

    No Known Activations