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

    Neuronpedia

    INDEX
    Explanations

    code syntax like curly braces and keywords such as "public", "class", or "import"

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lenker
    -0.56
     فريبيس
    -0.56
    ftagPool
    -0.54
     BorderRadius
    -0.52
    )++;
    -0.50
    Skocz
    -0.48
     насељу
    -0.48
    heça
    -0.47
     الدولى
    -0.47
    робнее
    -0.46
    POSITIVE LOGITS
    ↵↵
    0.81
    ädie
    0.58
    RegistryLite
    0.55
    HideFlags
    0.50
     Вікі
    0.49
    arxiv
    0.49
    ритори
    0.48
    AutoresizingMask
    0.48
    FailureListener
    0.47
     FormsModule
    0.47
    Act Density 0.347%

    No Known Activations