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

    Neuronpedia

    INDEX
    Explanations

    words indicating relationships or connections between entities

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

    and followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     setEmail
    -0.35
    tanleria
    -0.34
     his
    -0.33
     reve
    -0.31
     inc
    -0.30
     cla
    -0.28
    izielle
    -0.28
    beforeAll
    -0.28
     secret
    -0.27
     Hein
    -0.27
    POSITIVE LOGITS
    AndroidJUnit
    0.68
    Personensuche
    0.66
    StructEnd
    0.66
     esternos
    0.65
     CreateTagHelper
    0.64
     ProtoMessage
    0.63
    aarrggbb
    0.62
     informée
    0.62
     ब्रेकडाउन
    0.60
    tagHelperRunner
    0.60
    Act Density 0.049%

    No Known Activations