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

    Neuronpedia

    INDEX
    Explanations

    references to possession or support

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

    possessive pronoun + feeling/opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.53
    writeFieldEnd
    -0.51
     Hedges
    -0.47
     <<<<<<<<<<<<<<
    -0.47
    sizeCache
    -0.47
    ⪜
    -0.46
    UrlResolution
    -0.46
    zerland
    -0.46
    حوالہ
    -0.46
    dusty
    -0.45
    POSITIVE LOGITS
     vœux
    0.52
    queryInterface
    0.46
    Heraus
    0.41
     mergeFrom
    0.40
     dieux
    0.35
     bertambah
    0.35
     påvir
    0.34
    PhysRevD
    0.33
     görüş
    0.33
     vœ
    0.32
    Act Density 0.024%

    No Known Activations