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

    Neuronpedia

    INDEX
    Explanations

    references to social media platforms and statistical data representations

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

    social media and histograms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.60
    ChildScrollView
    -0.54
    contentLoaded
    -0.54
    ValueStyle
    -0.51
    TemporalType
    -0.49
    ThroughAttribute
    -0.48
    DockStyle
    -0.47
     NSCoder
    -0.47
    baric
    -0.47
     Bono
    -0.46
    POSITIVE LOGITS
     Instagram
    1.73
    Instagram
    1.66
     instagram
    1.48
    instagram
    1.36
     INSTAGRAM
    1.34
    INSTAGRAM
    1.26
     Insta
    0.77
     twitter
    0.75
    インスタ
    0.74
     Twitter
    0.73
    Act Density 0.002%

    No Known Activations