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

    Neuronpedia

    INDEX
    Explanations

    references to belief or faith in a religious context

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

    Follows "to" or contains numbers

    np_acts-logits-general · gemini-2.0-flash

    "to" followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.66
    ,
    -0.58
    .
    -0.52
     
    -0.50
     two
    -0.49
     of
    -0.48
     and
    -0.47
    –
    -0.46
     (
    -0.45
    うちに
    -0.45
    POSITIVE LOGITS
    تقاوى
    1.48
     متعلقه
    1.35
    TypedDataSet
    1.28
     дописавши
    1.18
    GEBURTSDATUM
    1.16
     CreateTagHelper
    1.14
    uxxxx
    1.14
    IntoConstraints
    1.14
     NSCoder
    1.10
     ModelExpression
    1.10
    Act Density 0.402%

    No Known Activations