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

    Neuronpedia

    INDEX
    Explanations

    elements related to web navigation controls

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

    user interaction with UI elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bewerken
    -0.58
     propOrder
    -0.53
    hlung
    -0.51
    蚪
    -0.50
     виправивши
    -0.48
     Casey
    -0.47
    verifyException
    -0.46
    appé
    -0.45
    */),
    -0.45
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
     pleaſure
    0.46
     juſ
    0.39
     neceſſ
    0.38
    ſelf
    0.38
    badlogic
    0.38
    الحياه
    0.37
     kasarigan
    0.34
     Diſ
    0.33
     viſ
    0.33
     myſelf
    0.32
    Act Density 0.001%

    No Known Activations