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

    Neuronpedia

    INDEX
    Explanations

    references to scientific measurements or parameters related to performance and efficiency

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

    Mathematical or scientific expressions

    np_acts-logits-general · gemini-2.0-flash

    \mathrm text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Her
    -0.47
     Mor
    -0.44
     an
    -0.43
     Mon
    -0.43
     mor
    -0.42
     process
    -0.42
     M
    -0.42
     some
    -0.41
     glass
    -0.40
    mius
    -0.40
    POSITIVE LOGITS
    AddTagHelper
    0.99
    sizeCache
    0.92
     ExecuteAsync
    0.88
     NSCoder
    0.85
    Personendaten
    0.85
    InjectAttribute
    0.84
    InvalidProtocol
    0.83
    LookAnd
    0.83
     lenker
    0.80
     <=",
    0.78
    Act Density 0.210%

    No Known Activations