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

    Neuronpedia

    INDEX
    Explanations

    references to color attributes and formatting in UI design

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

    Phone numbers or codes

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by colors or units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hel
    -0.45
    getattr
    -0.41
     hal
    -0.41
     Help
    -0.41
    dubbo
    -0.38
     Tech
    -0.38
    寄せ
    -0.38
    Orphan
    -0.37
    Help
    -0.37
     Hel
    -0.36
    POSITIVE LOGITS
     تضيفلها
    0.96
     pleaſure
    0.91
     purpoſe
    0.87
     Monfieur
    0.85
     Majefty
    0.83
    ChildScrollView
    0.81
     ſtre
    0.80
     ویکی‌پدیای
    0.77
     fubject
    0.75
     diſt
    0.74
    Act Density 0.109%

    No Known Activations