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

    Neuronpedia

    INDEX
    Explanations

    references to specific facts or assertions

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

    the fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.45
    awtextra
    -0.40
     <<<<<<<<<<<<<<
    -0.40
    Välislingid
    -0.40
    silueta
    -0.40
     Besoin
    -0.38
    instancetype
    -0.36
     assisti
    -0.36
     Reine
    -0.36
    PreferredItem
    -0.35
    POSITIVE LOGITS
     GetYourGuide
    0.47
    liferay
    0.46
     noqa
    0.46
    MLLoader
    0.44
    didSet
    0.43
     betweenstory
    0.43
    /**
    0.42
    XmlIgnore
    0.42
    typeorm
    0.41
     ""],
    0.40
    Act Density 0.062%

    No Known Activations