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

    Neuronpedia

    INDEX
    Explanations

    references to increasing dosage or workload in training and medical contexts

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

    quantified increases and decreases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    はじめに
    -0.57
    XmlAccessType
    -0.52
    WithIOException
    -0.50
    Derbyniad
    -0.49
     विश्वसनीयता
    -0.49
    ngdoc
    -0.47
    NameInMap
    -0.46
     ligiloj
    -0.46
    FormTagHelper
    -0.46
     censiti
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.44
     başar
    0.38
    DockStyle
    0.38
    lasyon
    0.36
    break
    0.33
     Infór
    0.33
     magasins
    0.31
     Selatan
    0.31
     inappropriés
    0.30
     réguli
    0.30
    Act Density 0.179%

    No Known Activations