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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurement accuracy and specificity in scientific contexts

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

    Describes a limit or measure of something

    np_acts-logits-general · gemini-2.0-flash

    performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.47
     cherchés
    -0.47
    Verkehr
    -0.46
    énario
    -0.44
    sweise
    -0.44
     gezet
    -0.44
    ungalows
    -0.44
    SharedCtor
    -0.42
    recated
    -0.41
     виправивши
    -0.40
    POSITIVE LOGITS
     enhancement
    0.71
     improvement
    0.65
     enhancements
    0.65
     improvements
    0.62
     levels
    0.61
     increase
    0.60
     boost
    0.60
     tinggi
    0.58
     enhancer
    0.57
    enhancing
    0.57
    Act Density 1.203%

    No Known Activations